© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 177378
    Prev
    Next
    INDEX
    Explanations

    vision, mission statements

    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_29_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
     customization
    0.44
     lungs
    0.43
     '\''
    0.39
     mett
    0.38
     カスタ
    0.38
     sécurité
    0.38
    ['
    0.38
     dependency
    0.38
    Datas
    0.38
    ';"/>
    0.38
    POSITIVE LOGITS
    antage
    0.42
     القاعدة
    0.37
     موسي
    0.36
    天天
    0.35
     Kohl
    0.34
    ilizce
    0.34
    iggio
    0.34
    vered
    0.34
    之旅
    0.34
    aranth
    0.34
    Activations Density 0.007%

    No Known Activations