© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 549
    Prev
    Next
    INDEX
    Explanations

    code snippets and markup, including commands, variable declarations, and file paths.

    oai_token-act-pair · gemini-2.0-flash

    public

    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
    iotensin
    -0.56
    ">)</
    -0.54
    ască
    -0.53
    TypedDataSet
    -0.52
    MouseButton
    -0.51
    <caption>
    -0.51
    getWriter
    -0.51
    endpush
    -0.51
    enação
    -0.50
    ticelli
    -0.50
    POSITIVE LOGITS
     Biôgrafia
    0.54
    gameserver
    0.53
    astéro
    0.53
     Adhe
    0.51
    LookAnd
    0.51
    
    0.50
    NameInMap
    0.50
    Portail
    0.49
     réguli
    0.47
    invokeLater
    0.47
    Activations Density 13.590%

    No Known Activations