© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225914
    Prev
    Next
    INDEX
    Explanations

    farm contexts

    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_10_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
    op
    0.81
    り
    0.79
    ua
    0.69
    ين
    0.68
    w
    0.68
    un
    0.68
    ens
    0.67
    বর্ত
    0.66
     europeos
    0.63
    い
    0.63
    POSITIVE LOGITS
    (
    0.87
    [
    0.73
     acetylation
    0.71
     gahet
    0.68
    ;
    0.68
     intercepts
    0.67
    ;(
    0.63
     fibers
    0.62
     insertions
    0.62
     curvatures
    0.62
    Activations Density 0.002%

    No Known Activations