© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 46400
    Prev
    Next
    INDEX
    Explanations

    makefile syntax

    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_22_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
     Palma
    0.46
     प्रथा
    0.44
     certos
    0.44
     Cada
    0.43
     Recherche
    0.43
    國家
    0.42
     Systematic
    0.41
     国家
    0.41
    횃
    0.41
     जानना
    0.41
    POSITIVE LOGITS
     nurs
    0.41
    צ
    0.41
     injuring
    0.41
     ጡ
    0.40
    න්ධ
    0.37
     robbing
    0.37
     nurse
    0.37
    ಾನ್
    0.37
    popupButton
    0.37
    js
    0.36
    Activations Density 0.000%

    No Known Activations