© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124727
    Prev
    Next
    INDEX
    Explanations

    ZDX Hatch, ZDNet, Zdfgfdhgdfh

    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
     on
    0.83
    '
    0.82
    টি
    0.81
    t
    0.80
    H
    0.80
    ب
    0.78
    !
    0.77
     the
    0.76
    를
    0.76
     an
    0.73
    POSITIVE LOGITS
    %、
    0.68
     étamines
    0.66
     comod
    0.66
    の後
    0.65
    Cemento
    0.64
     echoed
    0.63
    ्यूट
    0.62
    elementReference
    0.62
    ยิน
    0.62
     échantillons
    0.62
    Activations Density 0.000%

    No Known Activations