© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 54595
    Prev
    Next
    INDEX
    Explanations

    questions and seeking answers

    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_30_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
     어려
    0.47
     등이
    0.42
     обеспечение
    0.41
    很是
    0.41
     sebagainya
    0.41
     др
    0.39
    ]$;
    0.38
     ऐसा
    0.38
     등을
    0.38
     całość
    0.38
    POSITIVE LOGITS
     quatro
    0.46
     four
    0.43
     five
    0.41
     నాలుగు
    0.41
    នៅក្នុង
    0.39
    4
    0.39
     ثلاث
    0.38
     cinq
    0.38
     neoplasms
    0.38
     rained
    0.38
    Activations Density 0.001%

    No Known Activations