© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 26623
    Prev
    Next
    INDEX
    Explanations

    library card, orientation, system

    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_40_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
    <tr>
    0.35
     coloqu
    0.35
     മാന
    0.34
     Chilton
    0.34
     اجازه
    0.33
    焱
    0.33
     Kal
    0.33
    vang
    0.32
     окно
    0.32
    葵
    0.32
    POSITIVE LOGITS
     libraries
    0.54
     Libraries
    0.48
     System
    0.45
     hệ
    0.45
     library
    0.45
     system
    0.44
     библиотеки
    0.43
     bibli
    0.43
     Bibli
    0.43
    Libraries
    0.43
    Activations Density 0.002%

    No Known Activations