© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 47057
    Prev
    Next
    INDEX
    Explanations

    grid dimensions or counts

    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_13_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
    st
    0.50
     if
    0.50
    Is
    0.49
     in
    0.48
    M
    0.47
    ד
    0.46
    mo
    0.46
    ’
    0.45
    '
    0.44
    AMS
    0.43
    POSITIVE LOGITS
    ਣਾ
    0.49
     thiện
    0.47
     parois
    0.47
    ٦
    0.47
    ācijas
    0.45
    ERON
    0.45
    ۶
    0.44
     privadas
    0.44
    țile
    0.44
     ಅಗ
    0.43
    Activations Density 0.024%

    No Known Activations