© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 130540
    Prev
    Next
    INDEX
    Explanations

    Sam Altman, Sam Rockwell, Samurai, Samut

    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_1_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
    ні
    1.35
    𝐡
    1.16
    ן
    1.14
    ль
    1.09
    ्स
    1.03
    𝐬
    1.00
    ها
    0.98
    ла
    0.94
    льну
    0.94
    LI
    0.93
    POSITIVE LOGITS
     for
    1.27
    して
    1.23
    for
    1.17
    と
    1.15
    ে
    1.14
    한
    1.13
    ある
    1.12
    ä
    1.09
    お
    1.09
    し
    1.08
    Activations Density 0.001%

    No Known Activations