© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 24992
    Prev
    Next
    INDEX
    Explanations

    say "oz"

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
     an
    0.53
     uz
    0.50
    Uz
    0.46
     Uz
    0.43
     уз
    0.38
     Uzbekistan
    0.35
    വ്യ
    0.35
    romagnet
    0.33
     บน
    0.33
    ','%
    0.33
    POSITIVE LOGITS
     O
    0.61
     ounces
    0.57
     tablespoons
    0.54
     kilograms
    0.52
     Kil
    0.51
     grams
    0.51
     teaspoons
    0.51
     kilobytes
    0.47
    온
    0.47
     yards
    0.46
    Activations Density 0.002%

    No Known Activations