© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124810
    Prev
    Next
    INDEX
    Explanations

    microvascular complications

    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_3_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
    an
    0.68
    cak
    0.63
    her
    0.61
    unet
    0.60
    ard
    0.59
    he
    0.57
    t
    0.57
    ning
    0.57
    alt
    0.57
    ud
    0.56
    POSITIVE LOGITS
     to
    0.73
    د
    0.73
     tedesco
    0.70
    자
    0.69
    사이
    0.68
    기
    0.68
    ক
    0.67
    데이터
    0.67
    س
    0.65
     asta
    0.64
    Activations Density 0.001%

    No Known Activations