© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 11672
    Prev
    Next
    INDEX
    Explanations

    code formatting syntax

    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_40_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
    ¬
    0.52
     ¬
    0.41
    kl
    0.38
    Linq
    0.38
    ving
    0.38
    co
    0.36
    udin
    0.36
    agen
    0.36
    clare
    0.36
    ­
    0.36
    POSITIVE LOGITS
     `${
    1.01
     $"{
    0.87
     ${
    0.76
    `${
    0.75
    (`${
    0.73
    }>{
    0.73
    ($"{
    0.73
     "${
    0.71
     %><%=
    0.71
     '${
    0.68
    Activations Density 0.257%

    No Known Activations