© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 206945
    Prev
    Next
    INDEX
    Explanations

    ผลกระทบ

    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_6_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
    ب
    1.24
     CtApp
    1.15
     ૧
    1.14
     అయితే
    1.11
     可能
    1.06
    ב
    1.06
     言っ
    1.05
     វា
    1.05
     étaient
    1.04
     それ
    1.04
    POSITIVE LOGITS
    t
    1.60
    ar
    1.21
    l
    1.19
    er
    1.05
    I
    1.02
    v
    0.96
    en
    0.93
    arme
    0.89
    arne
    0.89
    -
    0.88
    Activations Density 0.000%

    No Known Activations