© 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. 26658
    Prev
    Next
    INDEX
    Explanations

    0

    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
    affected
    0.41
     Affected
    0.40
     Fin
    0.39
     affected
    0.38
     Continent
    0.38
    儆
    0.37
     Mildred
    0.37
    صاب
    0.37
    障害
    0.37
    Complexity
    0.36
    POSITIVE LOGITS
    picks
    0.43
     picks
    0.41
    தியான
    0.37
     ಉಳ
    0.37
    ेलो
    0.37
    pickup
    0.37
     ያስ
    0.35
     Picks
    0.35
    Newly
    0.35
    縞
    0.35
    Activations Density 0.010%

    No Known Activations