© 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. 126930
    Prev
    Next
    INDEX
    Explanations

    lists of answers

    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
     ranked
    0.45
    Stylesheet
    0.39
    绕
    0.37
    ጠቀ
    0.36
     rarely
    0.35
     puj
    0.35
    Weekday
    0.35
     kac
    0.35
     מער
    0.35
    сказа
    0.34
    POSITIVE LOGITS
    䧏
    0.44
    萑
    0.43
    찬
    0.40
     answers
    0.40
     réponses
    0.39
     compi
    0.39
     pertinente
    0.39
    讖
    0.38
     밀
    0.38
     فونی
    0.38
    Activations Density 0.000%

    No Known Activations