© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 7475
    Prev
    Next
    INDEX
    Explanations

    XML namespace declarations

    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_39_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
     SPARSE
    0.42
     overwhelmingly
    0.42
     క్యా
    0.40
    (__('
    0.37
    SetParameter
    0.37
    права
    0.37
    釐
    0.36
    指数
    0.36
     unobstructed
    0.36
    segments
    0.35
    POSITIVE LOGITS
    ersi
    0.41
    lee
    0.40
    condition
    0.40
    weixin
    0.40
    erro
    0.40
    Lee
    0.38
     нес
    0.38
     услови
    0.36
    ErrorCode
    0.36
    emakers
    0.36
    Activations Density 0.001%

    No Known Activations