© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 117459
    Prev
    Next
    INDEX
    Explanations

    fraction notation

    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_27_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
     може
    0.37
     Ва
    0.37
    Flex
    0.36
    <h2>
    0.36
    RealPath
    0.35
    发生在
    0.35
     О
    0.34
    тон
    0.34
    <table>
    0.34
    ιού
    0.34
    POSITIVE LOGITS
     demokrat
    0.42
     reconstit
    0.41
     rejecting
    0.37
     traitor
    0.37
     नैसर्गिक
    0.37
     संप
    0.37
     faucets
    0.37
     miraculously
    0.36
     ethyl
    0.36
     acreage
    0.36
    Activations Density 0.000%

    No Known Activations