© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31300
    Prev
    Next
    INDEX
    Explanations

    css, bootstrap, leaflet file paths

    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
    Not in Any Lists

    No Comments

    Negative Logits
    гети
    0.38
    醗
    0.38
    getPath
    0.38
     Emper
    0.38
    asInstanceOf
    0.38
    hej
    0.38
    Ener
    0.37
    RuL
    0.36
    propertyPath
    0.36
    鶏
    0.36
    POSITIVE LOGITS
     শ্রেণ
    0.42
     सीधी
    0.42
     демон
    0.39
    CLOSED
    0.38
     தரும்
    0.36
     प्रीमियम
    0.35
     Claims
    0.35
    ClassNotFound
    0.35
    Corps
    0.34
    浑
    0.34
    Activations Density 0.000%

    No Known Activations