© 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-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21303
    Prev
    Next
    INDEX
    Explanations

    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_56_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
    棋
    0.60
     chess
    0.56
     Chess
    0.51
     शतरंज
    0.46
    Chess
    0.44
     Schach
    0.43
    chess
    0.40
    ♟
    0.39
     chessboard
    0.39
     billi
    0.38
    POSITIVE LOGITS
     Go
    1.26
    Go
    1.10
    围
    0.90
    将
    0.90
    圍
    0.89
     Hold
    0.88
     Texas
    0.82
     Mah
    0.81
    Hold
    0.79
     mah
    0.78
    Activations Density 0.044%

    No Known Activations