© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39540
    Prev
    Next
    INDEX
    Explanations

    datos

    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
    岧
    0.58
     fondament
    0.56
     herd
    0.55
     développ
    0.55
    pèce
    0.55
     bánh
    0.54
     fundament
    0.52
    urup
    0.52
    וּ
    0.52
    Ꮰ
    0.52
    POSITIVE LOGITS
    1
    0.75
    ра
    0.71
    म
    0.69
    м
    0.68
    ри
    0.66
    ।
    0.66
    abouts
    0.66
    on
    0.64
    re
    0.64
    ها
    0.64
    Activations Density 0.000%

    No Known Activations