© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10463
    Prev
    Next
    INDEX
    Explanations

    people discussing playing video games

    oai_token-act-pair · gemini-2.0-flash

    games

    np_max-act-logits · gemini-2.0-flash

    play

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    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
     player
    -1.98
     game
    -1.91
     players
    -1.89
     Players
    -1.77
     Player
    -1.69
    Players
    -1.69
     games
    -1.68
    player
    -1.67
    Player
    -1.66
    game
    -1.64
    POSITIVE LOGITS
     للمعارف
    0.68
    enderror
    0.65
    TypedDataSet
    0.65
     فريبيس
    0.64
    tagHelperRunner
    0.62
    RenderAtEndOf
    0.61
    IsMutable
    0.60
    igshid
    0.60
    VersionUID
    0.59
    脚注の使い方
    0.58
    Activations Density 0.640%

    No Known Activations