© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43898
    Prev
    Next
    INDEX
    Explanations

    powerful feature introduced

    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_13_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
     certo
    0.55
     Treiber
    0.54
     Noord
    0.52
     febbraio
    0.52
    ‖</
    0.51
     prodotto
    0.50
     Sicily
    0.49
     Fontainebleau
    0.49
     Road
    0.49
     Gaut
    0.49
    POSITIVE LOGITS
    隈
    0.53
     entrevistas
    0.52
    رد
    0.51
    чі
    0.51
    Blogs
    0.51
    د
    0.50
    وس
    0.50
    Barnes
    0.50
    ز
    0.49
    الد
    0.49
    Activations Density 0.000%

    No Known Activations