© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 63715
    Prev
    Next
    INDEX
    Explanations

    pediatric care

    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_41_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
    ENT
    0.77
     Ear
    0.77
     ENT
    0.73
    Ear
    0.69
     ear
    0.68
     Nose
    0.67
     Ears
    0.67
    耳
    0.67
     nose
    0.65
     ears
    0.62
    POSITIVE LOGITS
    ミリー
    0.38
    щин
    0.37
     bahas
    0.37
    ቛ
    0.37
     ভাষার
    0.36
     sonora
    0.36
     carbono
    0.35
     RCLCPP
    0.35
    plicit
    0.34
     szcz
    0.34
    Activations Density 0.000%

    No Known Activations