© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 170479
    Prev
    Next
    INDEX
    Explanations

    tablespoon measurements followed by ingredients

    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_20_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
     じゃん
    0.47
     basé
    0.46
     appartenant
    0.45
    ㄞ
    0.44
     जैविक
    0.43
     sans
    0.43
     sque
    0.43
     lançamento
    0.43
    墉
    0.43
     régler
    0.42
    POSITIVE LOGITS
    த்த
    0.42
    প্রে
    0.41
    Pow
    0.39
    tev
    0.39
    tta
    0.39
     captures
    0.38
    டிய
    0.38
    lop
    0.38
    kannya
    0.37
    폴
    0.37
    Activations Density 0.002%

    No Known Activations