© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 31454
    Prev
    Next
    INDEX
    Explanations

    xml.etree.ElementTree as ET

    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
    으니
    0.39
    Dtls
    0.38
     thrust
    0.38
    veren
    0.38
    ASON
    0.37
     sparkle
    0.36
    旭
    0.36
     Typh
    0.36
     lim
    0.36
     physically
    0.35
    POSITIVE LOGITS
    લિક
    0.41
     publicación
    0.41
    ច្រើន
    0.41
     publicité
    0.40
    Dick
    0.40
     comando
    0.39
     tredje
    0.39
     Commandments
    0.38
    ^{-(
    0.38
    ди
    0.38
    Activations Density 0.000%

    No Known Activations