© 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. 19247
    Prev
    Next
    INDEX
    Explanations

    C++ build tools

    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
     header
    1.80
    头
    1.73
    header
    1.70
    頭
    1.64
     Header
    1.61
    Header
    1.60
     headers
    1.55
     head
    1.55
     头
    1.47
    Head
    1.45
    POSITIVE LOGITS
     coach
    0.74
     coaches
    0.68
     trainer
    0.66
    coach
    0.63
    Coach
    0.62
     Coach
    0.62
    Trainer
    0.60
    教练
    0.59
     Trainer
    0.58
     Coaches
    0.58
    Activations Density 0.006%

    No Known Activations