© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237389
    Prev
    Next
    INDEX
    Explanations

    take

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    섞
    0.43
     заключения
    0.41
    syscall
    0.37
    olol
    0.37
    شوف
    0.36
    発生
    0.36
    auto
    0.35
     স্যার
    0.35
    aiti
    0.35
    끽
    0.34
    POSITIVE LOGITS
     take
    0.52
     Take
    0.44
     TAKE
    0.43
     takes
    0.42
     fum
    0.41
     credit
    0.41
     Takes
    0.40
     Chartered
    0.40
     nehmen
    0.40
    راث
    0.38
    Activations Density 0.001%

    No Known Activations