© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 68306
    Prev
    Next
    INDEX
    Explanations

    Combat

    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_46_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
    1.14
     winning
    1.00
    win
    0.94
    WIN
    0.92
     wins
    0.92
    Win
    0.90
     Win
    0.89
    赢
    0.89
    winning
    0.88
    wins
    0.88
    POSITIVE LOGITS
    Combat
    0.46
     Combat
    0.46
    戦闘
    0.42
     combat
    0.41
     Grant
    0.41
    combat
    0.40
    μεριν
    0.40
     GRANT
    0.39
    meniz
    0.39
    㢼
    0.39
    Activations Density 0.053%

    No Known Activations