© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 92040
    Prev
    Next
    INDEX
    Explanations

    beautification, beautify, beautifull

    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_3_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
    that
    0.75
    ت
    0.74
    т
    0.72
    त
    0.72
    countable
    0.70
    although
    0.70
    tops
    0.68
    تبر
    0.68
    corr
    0.64
    then
    0.64
    POSITIVE LOGITS
     be
    1.02
     for
    1.00
     to
    1.00
     from
    0.84
    "
    0.81
     is
    0.77
     i
    0.73
     como
    0.70
     like
    0.66
     .
    0.64
    Activations Density 0.001%

    No Known Activations