© 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. 200289
    Prev
    Next
    INDEX
    Explanations

    mg followed by quantity

    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
    ات
    1.24
    -
    1.22
    on
    1.21
    is
    1.17
    ด
    1.11
    ac
    1.08
    u
    1.05
    其他
    1.05
    ط
    1.04
    ב
    1.03
    POSITIVE LOGITS
    ן
    1.56
     That
    1.04
     حسين
    0.97
     bhij
    0.95
     They
    0.93
     It
    0.90
     ناحيه
    0.90
    رويج
    0.89
    <0xF3>
    0.88
    راهيم
    0.88
    Activations Density 0.001%

    No Known Activations