© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16546
    Prev
    Next
    INDEX
    Explanations

    github.com URLs

    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_15_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
    法
    0.65
    技术的
    0.56
    法の
    0.56
    运算符
    0.54
     закона
    0.52
    法的
    0.51
    うまく
    0.51
    すると
    0.50
     jeopardize
    0.50
    谗
    0.49
    POSITIVE LOGITS
    ong
    0.59
    apartment
    0.59
    tan
    0.57
    phone
    0.56
    aking
    0.56
    AK
    0.56
    mä
    0.55
    ft
    0.55
     i
    0.55
    aria
    0.54
    Activations Density 0.000%

    No Known Activations