© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33704
    Prev
    Next
    INDEX
    Explanations

    Rate Law

    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_40_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
     Sealed
    0.48
     sealed
    0.46
    封
    0.45
     SEAL
    0.43
    sealed
    0.42
     seals
    0.41
     Seal
    0.41
     seal
    0.39
     Seals
    0.38
     ві
    0.38
    POSITIVE LOGITS
     कांस्टेबल
    0.38
    寰
    0.36
    छात्रा
    0.35
     거
    0.34
     ^{-
    0.34
    kii
    0.34
     promesa
    0.34
     oscill
    0.33
    ᐋ
    0.33
     ethane
    0.33
    Activations Density 0.010%

    No Known Activations