© 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. 200086
    Prev
    Next
    INDEX
    Explanations

    companies and reports

    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
     MAH
    0.40
    䀓
    0.39
     جم
    0.38
    ధాన
    0.38
     profiled
    0.36
     NAD
    0.36
     Tobacco
    0.36
     mã
    0.36
    Tobacco
    0.36
     руб
    0.36
    POSITIVE LOGITS
     tendances
    0.43
    悴
    0.42
     Schlag
    0.40
     tradeoffs
    0.38
    泼
    0.38
    ปัจจุบัน
    0.36
     satunya
    0.36
    圃
    0.35
     annual
    0.35
     commutation
    0.35
    Activations Density 0.000%

    No Known Activations