© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83176
    Prev
    Next
    INDEX
    Explanations

    special characters

    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_53_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
    ματα
    0.46
     {[
    0.41
    mbito
    0.39
     demean
    0.39
    deme
    0.38
    Myst
    0.37
     ‎
    0.37
    รวจ
    0.37
    datal
    0.36
    cua
    0.36
    POSITIVE LOGITS
    ਼
    0.46
    áč
    0.39
    ősz
    0.39
    නා
    0.38
    iul
    0.38
    łod
    0.38
    iß
    0.38
    áty
    0.38
    èmes
    0.37
    áis
    0.37
    Activations Density 0.002%

    No Known Activations