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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11657
    Prev
    Next
    INDEX
    Explanations

    discussion of video games

    oai_token-act-pair · gemini-2.0-flash

    code or programming-related terms

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

    game-related texts

    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
     game
    -1.54
     games
    -1.37
     gaming
    -1.31
    game
    -1.28
    games
    -1.20
     GAME
    -1.16
     videogame
    -1.14
    GAME
    -1.10
     Gaming
    -1.09
     GAMES
    -1.09
    POSITIVE LOGITS
     سكانية
    0.65
     GenerationType
    0.60
    )}</
    0.50
    })));
    0.49
    Rüyada
    0.49
    ultier
    0.49
    ɵɵelementStart
    0.49
     arşivlendi
    0.47
    发表于
    0.47
     تانيه
    0.46
    Activations Density 0.674%

    No Known Activations