© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 33462
    Prev
    Next
    INDEX
    Explanations

    special characters, programming concepts, or JSON

    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_3_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
    E
    0.70
     academically
    0.64
    ية
    0.63
    h
    0.62
    ↵↵↵
    0.62
    星
    0.62
    A
    0.61
     unabhängig
    0.60
    ஆம்
    0.59
    人們
    0.59
    POSITIVE LOGITS
    ag
    0.71
     GGA
    0.71
    ’
    0.69
    ิ
    0.67
    ig
    0.66
    .,
    0.64
    क
    0.64
     CPUs
    0.63
     FTA
    0.62
    ি
    0.61
    Activations Density 0.091%

    No Known Activations