© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1963
    Prev
    Next
    INDEX
    Explanations

    statistics for football teams and players

    oai_token-act-pair · gemini-2.0-flash

    statistical performance metrics in football

    np_token-act-pair-logits · gpt-4o-mini

    Sports statistics

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -1.51
    UnusedPrivate
    -1.24
     GenerationType
    -1.22
    AddTagHelper
    -1.15
    BeginContext
    -1.09
    ConstraintMaker
    -1.08
     ModelExpression
    -1.05
    PMailer
    -1.04
     Efq
    -1.04
    DockStyle
    -1.03
    POSITIVE LOGITS
    ,
    0.54
     as
    0.53
    .
    0.51
     and
    0.48
     in
    0.46
     with
    0.45
     for
    0.43
     mo
    0.43
     on
    0.42
     &
    0.40
    Activations Density 0.949%

    No Known Activations