© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81154
    Prev
    Next
    INDEX
    Explanations

    degree in Computer Science

    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_31_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
    િર
    0.43
    ufen
    0.38
     további
    0.36
    ሌ
    0.36
    ریس
    0.36
    atherapy
    0.36
    ุป
    0.35
    uirre
    0.35
    agré
    0.35
    🥂
    0.35
    POSITIVE LOGITS
    hound
    0.46
     b
    0.44
     PROFESSION
    0.42
     ਜਾਂ
    0.39
     or
    0.39
    هان
    0.39
     profesion
    0.38
     Appraisal
    0.38
    )|^
    0.38
     atau
    0.37
    Activations Density 0.000%

    No Known Activations