© 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. 16250
    Prev
    Next
    INDEX
    Explanations

    urology health

    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
     Entropy
    0.42
     انتظار
    0.39
     kidney
    0.38
     lingering
    0.38
     Returning
    0.37
    ecido
    0.37
     ecological
    0.36
     //!
    0.36
     VOLUME
    0.36
     encontrado
    0.35
    POSITIVE LOGITS
    Cook
    0.37
     सिंप
    0.37
    وە
    0.37
     Hewlett
    0.36
    wa
    0.36
    وه
    0.36
    Toc
    0.36
     মনীষ
    0.35
    بارك
    0.35
    ioners
    0.35
    Activations Density 0.004%

    No Known Activations