© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 142547
    Prev
    Next
    INDEX
    Explanations

    grain of salt

    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_12_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
    ーズ
    0.48
    -
    0.47
    ಟ್‌
    0.46
    されています
    0.46
    加快
    0.45
    anners
    0.45
    ्यां
    0.44
    acji
    0.43
    ционное
    0.43
     tradición
    0.43
    POSITIVE LOGITS
    鿢
    0.67
     الأ
    0.65
    ר
    0.65
     سي
    0.64
     rifi
    0.61
    ر
    0.61
     refusing
    0.61
    ي
    0.60
    QI
    0.59
     pericol
    0.59
    Activations Density 0.006%

    No Known Activations