© 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. 32-GEMMASCOPE-2-TRANSCODER-262K
    7. 238659
    Prev
    Next
    INDEX
    Explanations

    numbers and currency

    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_32_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
     idempotent
    0.38
    తాయి
    0.35
     Catalina
    0.35
     መቀ
    0.34
    搅拌
    0.34
     marihuana
    0.33
     proclaimed
    0.33
     Observed
    0.33
    用
    0.33
    ラ
    0.33
    POSITIVE LOGITS
     negotiations
    0.43
     woodwork
    0.41
     पिटाई
    0.41
    elij
    0.40
     perdre
    0.39
    ifice
    0.38
    balances
    0.38
    audience
    0.38
    ulitan
    0.37
    loser
    0.36
    Activations Density 0.000%

    No Known Activations