© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9689
    Prev
    Next
    INDEX
    Explanations

    various terms that look like titles/headers

    oai_token-act-pair · gemini-2.0-flash

    computer code and website design

    np_max-act · gemini-2.0-flash

    say "leading space" Method used: 2 — tokens all start with a leading space; say "leading space"

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -0.90
     themſelves
    -0.88
     myſelf
    -0.87
     purpoſe
    -0.84
     pleaſure
    -0.82
     Monfieur
    -0.81
     raiſ
    -0.80
     reaſon
    -0.78
     himſelf
    -0.77
     uſed
    -0.76
    POSITIVE LOGITS
    
    0.91
    #+#
    0.85
    ImageField
    0.83
     IndexPath
    0.82
    EndContext
    0.82
     Audiodateien
    0.80
    BASEPATH
    0.77
     TextStyle
    0.75
    WebElementEntity
    0.75
    KommentareTeilen
    0.74
    Activations Density 4.949%

    No Known Activations