© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 43728
    Prev
    Next
    INDEX
    Explanations

    prepuce, scalp, nipple, business, account

    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_13_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
     Chois
    0.35
    Мы
    0.33
     मंत्रिम
    0.33
    <0xD9>
    0.33
     команд
    0.33
    荃
    0.33
     organiques
    0.32
    ంలో
    0.32
     Мы
    0.32
     мастер
    0.32
    POSITIVE LOGITS
    os
    0.38
    o
    0.38
    are
    0.37
    ent
    0.36
    enciar
    0.35
    ́t
    0.35
    es
    0.35
    t
    0.34
    as
    0.34
    an
    0.33
    Activations Density 0.057%

    No Known Activations