© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 38329
    Prev
    Next
    INDEX
    Explanations

    language and concepts

    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_3_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
     ﺍ
    0.76
     présente
    0.71
     Docsity
    0.71
     Щ
    0.70
     দ্য
    0.70
    affiliated
    0.68
    vgili
    0.66
     गुना
    0.66
     presenti
    0.66
    ക
    0.65
    POSITIVE LOGITS
    ح
    0.93
    نا
    0.88
    ون
    0.81
    人
    0.77
    ان
    0.73
    دت
    0.72
    س
    0.72
    ست
    0.72
    ่า
    0.70
    an
    0.70
    Activations Density 0.000%

    No Known Activations