© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 197948
    Prev
    Next
    INDEX
    Explanations

    OpenMP pragmas

    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_12_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
    ष्‍ट
    0.50
     स्पर्श
    0.48
    ="<?
    0.47
     unión
    0.47
    gluten
    0.46
    添加
    0.46
     mudah
    0.46
     sporty
    0.45
    Iterations
    0.45
    టి
    0.44
    POSITIVE LOGITS
     поля
    0.50
    ﺭ
    0.50
    ան
    0.49
    να
    0.47
    лина
    0.47
     veracity
    0.47
     год
    0.46
     cyberspace
    0.46
    պես
    0.46
    фе
    0.45
    Activations Density 0.001%

    No Known Activations