© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 148496
    Prev
    Next
    INDEX
    Explanations

    webpack plugins

    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_23_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
     Tyr
    0.38
    ⁴
    0.37
    Tyr
    0.36
     wholly
    0.36
    効果
    0.34
    --)
    0.34
    ymoon
    0.33
     '=',
    0.33
     разными
    0.33
     effect
    0.33
    POSITIVE LOGITS
     близь
    0.37
     nodules
    0.36
     Agarwal
    0.36
    etli
    0.35
     іх
    0.35
     Kanpur
    0.35
     الساعه
    0.35
    ␊
    0.35
     Kejriwal
    0.35
     Bedi
    0.35
    Activations Density 0.000%

    No Known Activations