© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39935
    Prev
    Next
    INDEX
    Explanations

    jenkinsfile or files

    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_3_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
    。
    0.66
    $.
    0.64
     धमाकेदार
    0.64
     abandonar
    0.63
     думаю
    0.62
     a
    0.61
    ты
    0.61
     Actualmente
    0.61
     i
    0.61
    ום
    0.61
    POSITIVE LOGITS
    ↵
    1.31
    in
    0.72
    U
    0.72
    K
    0.71
    esthetics
    0.67
    E
    0.64
    an
    0.64
    AN
    0.62
    It
    0.61
    5
    0.61
    Activations Density 0.001%

    No Known Activations