© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2330
    Prev
    Next
    INDEX
    Explanations

    medical professional or doctor

    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_40_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
     enrolled
    0.38
    sample
    0.37
    サンプル
    0.37
     aján
    0.37
     છ
    0.36
     topik
    0.36
    æk
    0.36
    imwrite
    0.35
    Enroll
    0.35
     quiz
    0.35
    POSITIVE LOGITS
     कैप
    0.47
    を受
    0.45
     cap
    0.40
     gérer
    0.39
     w
    0.38
     Cod
    0.38
     دیر
    0.38
     Curse
    0.38
    旌
    0.38
     gem
    0.37
    Activations Density 0.047%

    No Known Activations