© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 201721
    Prev
    Next
    INDEX
    Explanations

    along

    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_37_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ﻅ
    0.41
    砂糖
    0.40
    兒童
    0.39
    >((
    0.39
     desider
    0.38
    ডিয়া
    0.38
     butch
    0.38
    込んで
    0.38
     ederek
    0.37
     tropical
    0.37
    POSITIVE LOGITS
     상세보기
    0.38
    ✶
    0.38
     CME
    0.37
     през
    0.37
     Related
    0.36
     related
    0.36
     Daniele
    0.36
    eos
    0.36
    鏡
    0.35
    CLK
    0.35
    Activations Density 0.000%

    No Known Activations