© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 67435
    Prev
    Next
    INDEX
    Explanations

    numerals and punctuation

    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_41_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    沱
    0.38
    णू
    0.37
     Gains
    0.36
     tehát
    0.36
     feas
    0.36
     incorporated
    0.36
    णु
    0.35
     oreille
    0.35
     guaranteed
    0.34
    ण्यास
    0.34
    POSITIVE LOGITS
    iors
    0.42
     ሀ
    0.40
    lice
    0.38
    ":[{"
    0.38
    ettivo
    0.37
    Bos
    0.37
    ('')
    0.36
    followlike
    0.36
    ''}
    0.36
    ior
    0.35
    Activations Density 0.003%

    No Known Activations