© 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. 14425
    Prev
    Next
    INDEX
    Explanations

    truncated text or data in tables

    oai_token-act-pair · 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
    例文帳に追加
    -0.55
     fittest
    -0.53
    templateUrl
    -0.48
    clusal
    -0.44
     assaults
    -0.44
     RTP
    -0.44
    SSP
    -0.44
    addChild
    -0.43
    OOP
    -0.43
     OSP
    -0.43
    POSITIVE LOGITS
    ::::::::
    0.77
     AssemblyCulture
    0.62
    ArrowToggle
    0.60
     للاسماء
    0.59
    featureID
    0.54
    findpost
    0.51
    NOPQRST
    0.51
    gameserver
    0.49
    ViewFeatures
    0.49
    DoubleQuotes
    0.49
    Activations Density 0.985%

    No Known Activations