© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 53633
    Prev
    Next
    INDEX
    Explanations

    Mind

    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_55_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
    υπ
    0.39
    ttamente
    0.39
    .").
    0.36
    鋪
    0.35
     ແມ່ນ
    0.35
    盎
    0.35
    ແມ່ນ
    0.35
    हालय
    0.34
    一般的な
    0.34
    粎
    0.34
    POSITIVE LOGITS
     Various
    1.93
     various
    1.90
    Various
    1.87
    various
    1.83
     berbagai
    1.56
    各种
    1.46
     çeşitli
    1.41
     diversos
    1.39
     различных
    1.38
    各種
    1.35
    Activations Density 0.004%

    No Known Activations