© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7307
    Prev
    Next
    INDEX
    Explanations

    statistics, stats, median, mean, data

    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_39_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ена
    0.40
    Grid
    0.38
    Ellen
    0.38
    鄔
    0.38
    gpu
    0.37
     пло
    0.36
     gpu
    0.36
     HIR
    0.36
    Collide
    0.36
    钿
    0.35
    POSITIVE LOGITS
     data
    0.82
     averages
    0.80
     Data
    0.74
     mean
    0.72
     Mean
    0.72
    data
    0.71
     sample
    0.71
     average
    0.71
     DATA
    0.71
     statistical
    0.70
    Activations Density 0.210%

    No Known Activations