© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 226667
    Prev
    Next
    INDEX
    Explanations

    DuckDuckGo

    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_10_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
    ية
    0.80
    د
    0.74
    ।
    0.73
    。
    0.73
    ль
    0.69
    زة
    0.69
    ג
    0.67
    変
    0.65
    ।।
    0.63
    中
    0.63
    POSITIVE LOGITS
     केवल
    0.64
     များ
    0.61
     Française
    0.60
    )
    0.60
     می‌کنند
    0.59
    and
    0.59
     Leland
    0.58
    corrected
    0.57
     sì
    0.57
     marchand
    0.57
    Activations Density 0.001%

    No Known Activations