© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 80708
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations

    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_53_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
     Kapital
    0.41
    veled
    0.40
     বাণিজ্যিক
    0.39
    spannung
    0.38
    theme
    0.38
     Chatham
    0.38
    ഷ
    0.37
    漿
    0.37
    ruc
    0.37
    اسية
    0.36
    POSITIVE LOGITS
    MG
    0.39
     Restricted
    0.38
     mg
    0.38
     enteral
    0.37
     विश्
    0.37
     identically
    0.37
     Mg
    0.36
     आयकर
    0.36
     restart
    0.36
     accumulate
    0.35
    Activations Density 0.002%

    No Known Activations