© 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. 88712
    Prev
    Next
    INDEX
    Explanations

    Formal, Pro, Cover, bugs, cell, test, strahlung

    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
    ing
    0.96
    ü
    0.94
    า
    0.88
    માં
    0.80
    ع
    0.74
    u
    0.71
    oh
    0.69
    of
    0.68
    the
    0.68
    ö
    0.64
    POSITIVE LOGITS
     sone
    0.57
    ومي
    0.54
    =>{
    0.52
    lerini
    0.51
     acht
    0.51
    lerin
    0.50
    getAsDouble
    0.50
     marcar
    0.50
    ши
    0.49
    เอียด
    0.49
    Activations Density 0.021%

    No Known Activations