© 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-3-27B-IT
    5. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94010
    Prev
    Next
    INDEX
    Explanations

    game variations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     अफ्री
    0.39
     niger
    0.38
    itorios
    0.37
    Kenya
    0.37
     afric
    0.36
     Система
    0.36
     Serengeti
    0.36
    藹
    0.36
    क्षी
    0.35
    евского
    0.35
    POSITIVE LOGITS
     game
    1.73
     Game
    1.63
    game
    1.55
    Game
    1.52
    ゲーム
    1.43
     GAME
    1.36
     게임
    1.34
    游戏
    1.27
    遊戲
    1.27
    เกม
    1.27
    Activations Density 0.001%

    No Known Activations