© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151288
    Prev
    Next
    INDEX
    Explanations

    programming syntax

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
    0.48
     and
    0.40
    _
    0.39
    Jordan
    0.38
    ...");
    0.37
    May
    0.37
    Advisor
    0.36
    prom
    0.35
    !");
    0.35
    promise
    0.35
    POSITIVE LOGITS
    [
    1.84
     [
    1.55
    [\
    1.13
    ()[
    1.11
     [_
    1.07
     [\
    1.06
    [(
    1.02
     [<
    1.02
    [_
    1.00
    ［
    1.00
    Activations Density 0.001%

    No Known Activations