© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 214829
    Prev
    Next
    INDEX
    Explanations

    institutional adoption

    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_31_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
     nuove
    0.44
     poop
    0.42
     pairings
    0.42
    pairwise
    0.42
    新たな
    0.40
    証
    0.40
     pairwise
    0.40
    苕
    0.39
    交易所
    0.38
     generative
    0.38
    POSITIVE LOGITS
    vacuum
    0.41
     fors
    0.38
    ced
    0.38
     කාල
    0.37
    Radio
    0.36
    LookAndFeels
    0.36
    šku
    0.36
     radios
    0.36
    ette
    0.36
     অক্ষ
    0.36
    Activations Density 0.002%

    No Known Activations