© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 35858
    Prev
    Next
    INDEX
    Explanations

    greatest of all time

    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_7_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
     a
    0.78
    a
    0.77
    o
    0.70
    ↵
    0.63
    er
    0.63
     United
    0.63
     is
    0.61
     {
    0.61
     variety
    0.61
     Trevor
    0.60
    POSITIVE LOGITS
     incisions
    0.67
    ों
    0.66
    ृ
    0.61
     introns
    0.61
     microtubules
    0.57
     tubules
    0.55
     catheters
    0.55
    Margins
    0.55
     nozzles
    0.54
     fibrils
    0.54
    Activations Density 0.007%

    No Known Activations