© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13250
    Prev
    Next
    INDEX
    Explanations

    code comments and execution output

    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_15_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
     hati
    0.61
    heart
    0.57
    for
    0.56
     heart
    0.54
     posled
    0.53
     for
    0.52
     maat
    0.52
     schematically
    0.51
     kaks
    0.51
    h
    0.50
    POSITIVE LOGITS
     ветра
    0.55
     prévoir
    0.52
    Mvc
    0.49
     intricacies
    0.49
     unsightly
    0.48
    ኔታ
    0.47
     între
    0.47
     ঐতিহ্য
    0.46
    มอบ
    0.46
    দ্র
    0.46
    Activations Density 0.018%

    No Known Activations