© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 45652
    Prev
    Next
    INDEX
    Explanations

    accordingly follows punctuation or instructions

    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
     (
    0.59
     bedre
    0.58
     зберіга
    0.58
     алып
    0.55
     проду
    0.54
     пят
    0.54
     i
    0.54
     [
    0.54
     Samaritan
    0.54
    natured
    0.54
    POSITIVE LOGITS
     interés
    0.59
    וס
    0.56
    ে
    0.55
    bois
    0.55
    Czas
    0.55
    ه‌های
    0.54
     veux
    0.54
    D
    0.54
    U
    0.53
    יי
    0.52
    Activations Density 0.002%

    No Known Activations