© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13241
    Prev
    Next
    INDEX
    Explanations

    words used in sports reporting, especially team names, competition, and statistics

    oai_token-act-pair · gemini-2.0-flash

    terms related to games

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

    say "game"

    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
    getWriter
    -0.48
    razza
    -0.44
    forChild
    -0.43
     chapter
    -0.42
     costumi
    -0.40
     dây
    -0.39
     maquinaria
    -0.38
     ballistic
    -0.37
    miss
    -0.37
     глава
    -0.36
    POSITIVE LOGITS
     games
    2.11
     game
    1.79
    games
    1.76
     Games
    1.63
    game
    1.58
     GAMES
    1.58
    Games
    1.57
     GAME
    1.40
    Game
    1.34
     juegos
    1.34
    Activations Density 1.387%

    No Known Activations