© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6534
    Prev
    Next
    INDEX
    Explanations

    numerical data with standard deviations

    oai_token-act-pair · gemini-2.0-flash

    +/-

    np_max-act · gemini-2.0-flash

    +/- Method used: 1 — because tokens consistently show plus/minus notation

    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_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    _
    -0.59
    $_['
    -0.55
     cuer
    -0.50
    Spoljašnje
    -0.50
    toHave
    -0.50
    >");
    -0.50
    >");
    -0.48
    ssysteme
    -0.48
    crumbs
    -0.48
    :],
    -0.48
    POSITIVE LOGITS
    SourceChecksum
    0.77
    IntoConstraints
    0.73
    /*
    0.64
    sendRedirect
    0.63
     ModelExpression
    0.63
     ExecuteAsync
    0.58
    onActivityResult
    0.57
    قایناق‌لار
    0.57
     defaultstate
    0.56
    LookAnd
    0.56
    Activations Density 1.753%

    No Known Activations