© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40781
    Prev
    Next
    INDEX
    Explanations

    dungeon crawl, model

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ي
    0.93
    ↵
    0.87
    </h3>
    0.83
    -
    0.80
    '
    0.77
    ↵↵
    0.77
    i
    0.75
    日期
    0.73
    游戏
    0.66
    时
    0.66
    POSITIVE LOGITS
    ні
    1.02
    ین
    0.88
    ی
    0.77
    ला
    0.75
    ری
    0.74
    ре
    0.71
    ため
    0.67
    یند
    0.66
    pendiente
    0.66
    s
    0.64
    Activations Density 0.000%

    No Known Activations