© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 148848
    Prev
    Next
    INDEX
    Explanations

    say "win" words

    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_59_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
     win
    3.81
    win
    3.11
     Win
    2.94
    Win
    2.80
     WIN
    2.03
    WIN
    1.97
    胜
    1.88
    勝
    1.84
     menang
    1.69
     승
    1.65
    POSITIVE LOGITS
    creas
    0.39
     sáng
    0.35
    చే
    0.32
    塬
    0.31
     Losing
    0.31
    Cxt
    0.31
    മാക
    0.31
    Divider
    0.31
    FONT
    0.30
    いただく
    0.30
    Activations Density 0.029%

    No Known Activations