© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 217
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with player-versus-player (PvP) game mechanics and balance

    oai_token-act-pair · gemini-2.0-flash

    sports players & teams

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     players
    -2.95
     player
    -2.95
     Players
    -2.80
    Players
    -2.70
     Player
    -2.67
    player
    -2.63
    Player
    -2.56
    players
    -2.52
     PLAYER
    -2.33
     PLAYERS
    -2.33
    POSITIVE LOGITS
    AddHtmlAttribute
    0.52
    󠁿
    0.48
     INTERESAR
    0.47
    NewUrlParser
    0.45
     wacht
    0.45
    itinéraire
    0.43
    ScopeManager
    0.43
    σμα
    0.42
    orance
    0.41
    Handlung
    0.41
    Activations Density 1.918%

    No Known Activations