© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 13805
    Prev
    Next
    INDEX
    Explanations

    terms related to organizations and events, especially those with acronyms or related to specific dates

    oai_token-act-pair · gemini-2.0-flash

    2

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
     pyplot
    -0.48
    byen
    -0.46
     focused
    -0.45
    Jereo
    -0.42
    nextInt
    -0.42
    setField
    -0.41
    İstinadlar
    -0.41
     broad
    -0.41
    fieldLabel
    -0.41
    protoimpl
    -0.40
    POSITIVE LOGITS
    Geplaatst
    0.91
    tagHelperRunner
    0.83
    StoryboardSegue
    0.82
    sizeCache
    0.79
     المعيارى
    0.77
     cauſe
    0.70
     itſelf
    0.69
     houſe
    0.68
     فريبيس
    0.67
    ]")]
    0.67
    Activations Density 2.094%

    No Known Activations