© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 84010
    Prev
    Next
    INDEX
    Explanations

    measure, indicator, representative

    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_29_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
    现状
    0.38
    成功
    0.38
     marg
    0.37
    也不知道
    0.37
     margins
    0.36
     краю
    0.36
    办
    0.36
    极端
    0.35
    どころ
    0.35
     мало
    0.35
    POSITIVE LOGITS
    gp
    0.40
    raisers
    0.38
    listen
    0.38
    metric
    0.38
    sea
    0.38
    aggregation
    0.38
     evaluates
    0.37
     मैट्रिक
    0.37
     conveyor
    0.37
     depicts
    0.36
    Activations Density 0.028%

    No Known Activations