© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11648
    Prev
    Next
    INDEX
    Explanations

    physicians or officers

    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_13_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
     geométricas
    0.55
    нтэр
    0.54
     बताये
    0.54
    這裡是
    0.53
    逄
    0.53
     гульнявыя
    0.53
     ஒன்றியம்
    0.52
    حضرت
    0.52
    सरी
    0.52
     функция
    0.51
    POSITIVE LOGITS
    </code>
    0.67
     attain
    0.52
    `
    0.52
    ει
    0.50
    、
    0.50
    sh
    0.49
    </strong>
    0.49
     i
    0.49
    ":
    0.48
    Z
    0.48
    Activations Density 0.011%

    No Known Activations