© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    7. 154633
    Prev
    Next
    INDEX
    Explanations

    for loop syntax

    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_23_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
    佹
    0.41
    भूषण
    0.40
     proudly
    0.39
    تاة
    0.39
     দূত
    0.37
     Isol
    0.37
     wristwatch
    0.37
     desper
    0.37
    ahun
    0.37
    antoor
    0.36
    POSITIVE LOGITS
     feb
    0.39
     Colours
    0.38
     Committees
    0.37
    writeFileSync
    0.37
     Colors
    0.37
    ++.
    0.37
    াড়া
    0.37
    লেট
    0.36
     tapaht
    0.36
    髄
    0.36
    Activations Density 0.000%

    No Known Activations