© 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. 9792
    Prev
    Next
    INDEX
    Explanations

    words or symbols related to statistical analysis, especially including confidence intervals, ratios, and probabilities

    oai_token-act-pair · gemini-2.0-flash

    numerical analysis/statistics

    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
    <bos>
    -0.60
    respectively
    -0.45
    officially
    -0.45
    k
    -0.42
    ug
    -0.42
    na
    -0.42
    DecimalFormat
    -0.42
    QUART
    -0.41
    že
    -0.41
     mano
    -0.41
    POSITIVE LOGITS
    TintMode
    0.77
    webElementXpaths
    0.76
    oredCriteria
    0.75
    Personendaten
    0.71
    enumii
    0.69
     فريبيس
    0.65
    tagHelperRunner
    0.65
    [:,:,
    0.64
     Мексичка
    0.63
    ReusableCell
    0.63
    Activations Density 17.605%

    No Known Activations