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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 105600
    Prev
    Next
    INDEX
    Explanations

    foreign games

    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_44_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     পোষণ
    0.39
    eflow
    0.37
     Butler
    0.35
    詁
    0.34
     DCT
    0.33
     Hei
    0.33
     পরিশ্রম
    0.32
    ższ
    0.32
    塙
    0.32
    ंता
    0.31
    POSITIVE LOGITS
     games
    2.72
     игры
    2.52
     juegos
    2.47
    ゲーム
    2.44
     بازی
    2.38
    游戏
    2.38
     juego
    2.38
    遊戲
    2.38
     게임
    2.38
    games
    2.36
    Activations Density 0.174%

    No Known Activations