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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 195331
    Prev
    Next
    INDEX
    Explanations

    search and discovery

    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_27_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
    名
    0.41
     ட
    0.41
    Supporting
    0.40
    STOCK
    0.40
    Various
    0.39
    supporting
    0.39
     완
    0.38
    τα
    0.37
    Use
    0.37
    SUPPORT
    0.37
    POSITIVE LOGITS
     ढूं
    0.53
     jobSearch
    0.52
     menemukan
    0.46
     искать
    0.46
     mencari
    0.45
    찾
    0.45
     поиск
    0.45
     શોધ
    0.45
    utenants
    0.44
    查找
    0.44
    Activations Density 0.008%

    No Known Activations