© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 93957
    Prev
    Next
    INDEX
    Explanations

    say "of"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     “
    0.61
     \"
    0.59
     "
    0.54
     «
    0.54
     „
    0.53
     「
    0.48
     `
    0.48
     '
    0.46
     Wrong
    0.45
     ‘
    0.45
    POSITIVE LOGITS
     colours
    0.48
     colourful
    0.46
     guilt
    0.46
     guilty
    0.41
     times
    0.39
    colours
    0.38
     colour
    0.37
     helping
    0.36
     visibility
    0.36
    abling
    0.36
    Activations Density 0.001%

    No Known Activations