© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10665
    Prev
    Next
    INDEX
    Explanations

    proper nouns of football players, teams etc

    oai_token-act-pair · gemini-2.0-flash

    Wisconsin

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     nahilalakip
    -0.57
    idge
    -0.56
    SourceChecksum
    -0.53
    IsMutable
    -0.51
    DoubleQuotes
    -0.51
    ┻
    -0.50
    czę
    -0.49
    دانشنامهٔ
    -0.48
     turns
    -0.48
    RegressionTest
    -0.47
    POSITIVE LOGITS
     Wisconsin
    0.67
     UW
    0.62
    Wisconsin
    0.59
    CONSIN
    0.58
     WIS
    0.58
     WI
    0.55
     Appleton
    0.54
    makeConstraints
    0.54
     Swiss
    0.53
     onBind
    0.53
    Activations Density 0.514%

    No Known Activations