© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44571
    Prev
    Next
    INDEX
    Explanations

    words in multiple languages

    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
    Deve
    0.54
     Elemente
    0.53
    ुक्त
    0.52
    еме
    0.50
    คม
    0.49
    シミ
    0.49
     atthakath
    0.48
    د
    0.48
    Buildable
    0.48
    मि
    0.48
    POSITIVE LOGITS
     is
    0.57
    islav
    0.55
    t
    0.55
     př
    0.53
    [
    0.53
     deeply
    0.52
    ោម
    0.52
    nt
    0.51
    rels
    0.51
    órios
    0.51
    Activations Density 0.003%

    No Known Activations