© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 31677
    Prev
    Next
    INDEX
    Explanations

    visual appearance

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    관
    0.41
    ួ
    0.38
    借り
    0.37
     Karya
    0.37
     కార్య
    0.36
    advised
    0.36
    형
    0.36
     किरायेदारों
    0.36
    )$;
    0.35
    ریق
    0.35
    POSITIVE LOGITS
     отобра
    0.69
     appearance
    0.68
    図
    0.66
    圖
    0.66
     penampilan
    0.64
     tampil
    0.64
    图
    0.62
     megjelen
    0.61
     தோ
    0.59
    appearance
    0.59
    Activations Density 0.034%

    No Known Activations