© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4299
    Prev
    Next
    INDEX
    Explanations

    contextual cues and seems very sensitive to a variety of topics and stylistic elements: the presence of conditional words like "if," discussions involving food, the occurrence of gerunds, references to time, and even specific sentence structures/fragments.

    oai_token-act-pair · gemini-2.0-flash

    generic text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     so
    -0.41
    Datuak
    -0.41
     grà
    -0.40
     lại
    -0.40
     therefore
    -0.39
    tovers
    -0.38
     mondi
    -0.37
    Mojo
    -0.35
     Theſe
    -0.35
     mord
    -0.35
    POSITIVE LOGITS
    contentLoaded
    1.04
    ImageContext
    0.72
     ModelExpression
    0.71
    RenderAtEndOf
    0.71
    webElementXpaths
    0.69
     autorytatywna
    0.67
    DockStyle
    0.66
    SupportActionBar
    0.66
    ModelAdmin
    0.66
    
    0.65
    Activations Density 2.700%

    No Known Activations