© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35014
    Prev
    Next
    INDEX
    Explanations

    victim of

    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_11_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
     Dragon
    0.66
     Mor
    0.63
     on
    0.61
     On
    0.61
     Children
    0.59
     El
    0.59
    这
    0.59
     Dro
    0.58
     Having
    0.57
     Your
    0.57
    POSITIVE LOGITS
     criminality
    0.63
     plywood
    0.62
     motorists
    0.60
    🚥
    0.60
     antit
    0.60
     malignancy
    0.60
     incidences
    0.60
     acrylonitrile
    0.59
     motorist
    0.59
     antide
    0.58
    Activations Density 0.003%

    No Known Activations