© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 936
    Prev
    Next
    INDEX
    Explanations

    text with a distinctive layout, particularly associated with legal documents, numbered lists, and reference sections.

    oai_token-act-pair · gemini-2.0-flash

    Document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    Geplaatst
    -0.71
     وتسجيلات
    -0.66
    DataPropertyName
    -0.64
     ModelExpression
    -0.63
     Himo
    -0.62
    InitVars
    -0.61
     мәкал
    -0.60
    tagHelperRunner
    -0.60
     digitais
    -0.59
    featureID
    -0.58
    POSITIVE LOGITS
    '
    0.55
    AutoScale
    0.55
     
    0.50
    <bos>
    0.50
    </td>
    0.49
    ’
    0.49
    [
    0.48
    ...
    0.48
    SuppressWarnings
    0.48
     An
    0.47
    Activations Density 0.818%

    No Known Activations