© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15491
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related syntax, even with typos

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    وفاته
    -0.66
     /\.(
    -0.63
    Rüyada
    -0.61
    Fns
    -0.57
    Cyfeiriadau
    -0.56
    Билгалдахарш
    -0.55
    Tikang
    -0.54
    mapStateToProps
    -0.53
     onOptions
    -0.52
     phí
    -0.49
    POSITIVE LOGITS
    tvguidetime
    0.61
     незавершена
    0.54
     ModelExpression
    0.52
     भर
    0.52
    tinyos
    0.52
     상세
    0.51
    enumii
    0.51
    énario
    0.51
     BoxDecoration
    0.49
    PANY
    0.49
    Activations Density 24.666%

    No Known Activations