© 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. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 226457
    Prev
    Next
    INDEX
    Explanations

    repeated vowels for emphasis

    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_6_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
     ότι
    1.23
     was
    1.23
    s
    1.15
    ’
    1.13
    вЂ
    1.13
     a
    1.10
    ।’
    1.09
    ება
    1.09
     to
    1.08
     vì
    1.08
    POSITIVE LOGITS
    و
    1.58
    고
    1.31
    ла
    1.27
    다
    1.27
    .
    1.23
    at
    1.23
    ומי
    1.19
    你
    1.13
    عمل
    1.12
    ו
    1.09
    Activations Density 0.000%

    No Known Activations