© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 33721
    Prev
    Next
    INDEX
    Explanations

    scattered light and distribution

    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_40_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
     worldwide
    0.48
     pü
    0.42
     autour
    0.41
     redor
    0.40
     alrededor
    0.40
    alabel
    0.39
     rundt
    0.39
    륵
    0.39
     Worldwide
    0.38
     intorno
    0.38
    POSITIVE LOGITS
    wrap
    0.39
     পছ
    0.38
    wer
    0.37
    Emails
    0.35
     दिशा
    0.34
    cars
    0.34
     방향
    0.34
    ミル
    0.34
     richting
    0.34
    引
    0.34
    Activations Density 0.007%

    No Known Activations