© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 6356
    Prev
    Next
    INDEX
    Explanations

    mentions of playing games or having a role in something.

    oai_token-act-pair · gemini-2.0-flash

    terms related to games and play

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

    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
    meaux
    -0.50
    AddHtmlAttribute
    -0.50
    ษ
    -0.46
     nakalista
    -0.45
    ToolStrip
    -0.45
     createState
    -0.44
    ffel
    -0.43
    條
    -0.43
    Panels
    -0.43
    GOTREF
    -0.43
    POSITIVE LOGITS
     game
    1.96
    game
    1.69
     juego
    1.56
     games
    1.52
     playing
    1.46
     gioco
    1.46
     play
    1.42
     permainan
    1.41
     GAME
    1.41
     jeu
    1.40
    Activations Density 0.997%

    No Known Activations