© 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. 14396
    Prev
    Next
    INDEX
    Explanations

    required providers

    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
     protections
    0.38
    ന്തപു
    0.38
    ovane
    0.38
     regimes
    0.38
     protection
    0.36
    ätzen
    0.36
     scheme
    0.36
    保护
    0.36
    ंपूर्वी
    0.36
    鄢
    0.36
    POSITIVE LOGITS
     Juventus
    0.46
     Inner
    0.46
    Inner
    0.40
     सिरसा
    0.39
    inner
    0.39
     ekst
    0.39
    LU
    0.38
     Piedmont
    0.38
     African
    0.38
     Vu
    0.38
    Activations Density 0.000%

    No Known Activations