© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 4699
    Prev
    Next
    INDEX
    Explanations

    code comments and separators

    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_38_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
    Ⅶ
    0.39
    Cleared
    0.39
    <0xB3>
    0.38
     Clemson
    0.38
     MaterialApp
    0.38
    <unused568>
    0.38
    ⑦
    0.38
     FormData
    0.37
     vii
    0.37
    ၇
    0.37
    POSITIVE LOGITS
    Woo
    0.39
    Kon
    0.39
    production
    0.38
    knowledge
    0.38
    finaly
    0.37
    Zie
    0.37
    Yay
    0.37
     знания
    0.37
     শু
    0.37
    ഭ്യാ
    0.37
    Activations Density 0.018%

    No Known Activations