© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7448
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_39_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
    etz
    0.27
     построен
    0.27
    phill
    0.27
     hại
    0.26
    oxin
    0.26
     lana
    0.25
    ថ
    0.25
    傣
    0.25
     Calcul
    0.25
    ptidase
    0.25
    POSITIVE LOGITS
    بیر
    0.31
     بتاريخ
    0.30
     পাত
    0.30
    곤
    0.29
     الموسم
    0.29
    RequestParam
    0.28
     Rend
    0.28
    imported
    0.27
    namespace
    0.27
     midnight
    0.27
    Activations Density 0.002%

    No Known Activations