© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1778
    Prev
    Next
    INDEX
    Explanations

    terms related to video games

    oai_token-act-pair · gemini-2.0-flash

    formats or terms related to digital surveys or rewards

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

    Game or virtual environment

    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
    Negative Logits
    Games
    -0.79
     games
    -0.77
    games
    -0.75
     GAMES
    -0.70
     Games
    -0.68
    Game
    -0.67
     Spiele
    -0.67
     Game
    -0.65
    game
    -0.63
     game
    -0.63
    POSITIVE LOGITS
     '{@
    0.55
    BeginContext
    0.54
    Życiorys
    0.53
    Хьажоргаш
    0.53
     challenges
    0.52
    تقاوى
    0.52
    tagext
    0.52
     Trial
    0.51
    CopyWith
    0.51
    Trial
    0.49
    Activations Density 3.880%

    No Known Activations