© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 127764
    Prev
    Next
    INDEX
    Explanations

    local malicious

    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_37_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
     Freel
    0.38
    பாய்
    0.37
     Scouts
    0.36
    よいよ
    0.36
    Hou
    0.35
    Ampl
    0.35
     like
    0.35
    圭
    0.35
     Kyi
    0.34
    Limit
    0.34
    POSITIVE LOGITS
    柳
    0.39
    mike
    0.38
     tragedia
    0.37
     mimo
    0.37
     banca
    0.36
     Ramona
    0.35
     terracotta
    0.35
     لگانا
    0.35
    እና
    0.35
    িলি
    0.34
    Activations Density 0.000%

    No Known Activations