© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12744
    Prev
    Next
    INDEX
    Explanations

    football-related terms and analysis of football games.

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    SharedCtor
    -0.78
    protoimpl
    -0.70
     gainera
    -0.69
     surla
    -0.67
     estekak
    -0.66
    Билгалдахарш
    -0.66
     NSCoder
    -0.66
    UserScript
    -0.65
     Exacts
    -0.64
    gameserver
    -0.64
    POSITIVE LOGITS
     those
    0.53
    대로
    0.50
     he
    0.50
    Those
    0.47
     Those
    0.46
     He
    0.45
     dàn
    0.45
     Dunlap
    0.44
    utdown
    0.42
     separation
    0.42
    Activations Density 19.344%

    No Known Activations