© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193818
    Prev
    Next
    INDEX
    Explanations

    Hawthorne, Seward, Edwards

    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_4_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
    <0x0D>
    0.20
    '
    0.18
    :
    0.17
     on
    0.15
    <0x80>
    0.15
    м
    0.15
    </h2>
    0.14
    t
    0.13
    ম
    0.13
    </h1>
    0.13
    POSITIVE LOGITS
    지
    0.16
     Иң
    0.16
    ዃ
    0.15
     Пере
    0.15
    bedaan
    0.15
    conten
    0.15
    ール
    0.15
    бовать
    0.15
    ຼ
    0.15
    ጿ
    0.14
    Activations Density 0.001%

    No Known Activations