© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171208
    Prev
    Next
    INDEX
    Explanations

    medical procedures

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     Sur
    1.94
    Sur
    1.91
    sur
    1.74
     sur
    1.70
     SUR
    1.60
     수
    1.55
    SUR
    1.48
     surge
    1.46
     Surge
    1.41
    수
    1.39
    POSITIVE LOGITS
     //[
    0.38
    CHU
    0.37
    បែប
    0.37
     insensitive
    0.36
    চির
    0.35
     Richt
    0.34
     অপারেশন
    0.34
    __."
    0.33
    Operand
    0.33
    MEDICAL
    0.33
    Activations Density 0.003%

    No Known Activations