© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35936
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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_7_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
    ك
    0.91
    ق
    0.79
    ت
    0.74
    ص
    0.73
    ی
    0.73
    ب
    0.69
    ف
    0.69
    ের
    0.68
    ார்
    0.68
    ج
    0.67
    POSITIVE LOGITS
    <unused2121>
    0.59
     telah
    0.59
    ，
    0.53
     veya
    0.53
     หรือ
    0.53
    0.52
     of
    0.52
     ਜਾਂ
    0.50
    abia
    0.50
     was
    0.50
    Activations Density 0.005%

    No Known Activations