© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 32492
    Prev
    Next
    INDEX
    Explanations

    His

    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
     Trimble
    0.39
    怡
    0.38
    
    0.37
    ريم
    0.37
     برم
    0.36
     कांस
    0.35
     trim
    0.35
    FTA
    0.35
    壺
    0.35
     FXMLLoader
    0.35
    POSITIVE LOGITS
    His
    0.50
     His
    0.50
    Пи
    0.41
    aport
    0.40
    irt
    0.39
    astia
    0.39
    ergic
    0.38
    ೆಯಿಂದ
    0.38
    ент
    0.38
    ymmetry
    0.38
    Activations Density 0.000%

    No Known Activations