© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13435
    Prev
    Next
    INDEX
    Explanations

    terabytes

    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_15_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
    ۱
    0.28
    Use
    0.27
    Brown
    0.27
    ġ
    0.26
     W
    0.26
    HEAD
    0.26
    I
    0.26
     اليه
    0.26
    হতের
    0.26
    ITEM
    0.25
    POSITIVE LOGITS
     nuevos
    0.38
     degree
    0.33
     novos
    0.31
     grado
    0.30
    નો
    0.29
     mando
    0.29
     nueva
    0.29
     nuevas
    0.29
    ેર
    0.28
    ാ
    0.27
    Activations Density 0.020%

    No Known Activations