© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 9884
    Prev
    Next
    INDEX
    Explanations

    apples left

    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
    en
    0.52
    P
    0.52
    AS
    0.50
    0.48
    ag
    0.48
    og
    0.47
    <
    0.47
    ac
    0.46
    Smith
    0.46
    ak
    0.46
    POSITIVE LOGITS
    งิน
    0.60
    葡萄酒
    0.59
    ͊
    0.57
    🚈
    0.57
     何
    0.56
    ちな
    0.55
     Köz
    0.55
    ธุ์
    0.55
    銀行
    0.54
     금융
    0.54
    Activations Density 0.079%

    No Known Activations