© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 216075
    Prev
    Next
    INDEX
    Explanations

    you

    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_50_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
    udor
    0.42
     SUMMARY
    0.41
     approu
    0.41
     visas
    0.40
    Qr
    0.39
    SUMMARY
    0.38
     leves
    0.38
    허
    0.37
     Duma
    0.37
    वीय
    0.37
    POSITIVE LOGITS
     seraient
    0.47
     serait
    0.43
    would
    0.42
    開幕
    0.41
     उन्‍होंने
    0.39
     sarebbero
    0.38
     estaría
    0.38
     would
    0.38
    uxi
    0.37
    方向に
    0.37
    Activations Density 0.002%

    No Known Activations