© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7007
    Prev
    Next
    INDEX
    Explanations

    game winning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    Fetch
    0.37
    чого
    0.37
     COC
    0.37
     wpt
    0.36
    銚
    0.36
    afir
    0.36
     κό
    0.35
    Plans
    0.35
    srcset
    0.35
     OCA
    0.35
    POSITIVE LOGITS
     game
    0.66
    game
    0.59
     게임
    0.59
    游戏
    0.52
     गेम
    0.51
     승
    0.50
    ゲーム
    0.49
     గేమ్
    0.48
     oyun
    0.48
    게임
    0.47
    Activations Density 0.074%

    No Known Activations