© 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. 13326
    Prev
    Next
    INDEX
    Explanations

    action

    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
    L
    0.57
    Royal
    0.52
    How
    0.50
    R
    0.48
    Rate
    0.47
    RC
    0.47
    J
    0.47
    Wh
    0.46
    Sold
    0.46
    Par
    0.45
    POSITIVE LOGITS
    ázquez
    0.55
     Необходимо
    0.54
     સી
    0.54
     scooters
    0.54
     реки
    0.52
     ;,
    0.52
     කාල
    0.52
    ério
    0.51
    éis
    0.50
    nads
    0.50
    Activations Density 0.001%

    No Known Activations