© 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. 19216
    Prev
    Next
    INDEX
    Explanations

    integer sums or complements

    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
    䜌
    0.40
     TokenType
    0.39
    颳
    0.39
    fNil
    0.37
     ܡ
    0.37
     Mila
    0.36
     WR
    0.36
    鬏
    0.36
    swadian
    0.36
    semblance
    0.36
    POSITIVE LOGITS
    CK
    0.41
    urut
    0.41
    ANCE
    0.38
    POOL
    0.37
     stagn
    0.37
    िस्तान
    0.36
     pools
    0.36
    嚕
    0.36
    gement
    0.34
    urope
    0.34
    Activations Density 0.005%

    No Known Activations