© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 53298
    Prev
    Next
    INDEX
    Explanations

    century, year, May, BCE

    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_30_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
     jugu
    0.38
     ferries
    0.37
    /*',
    0.35
    ቱ
    0.34
     সংখ্যাল
    0.33
    篠
    0.33
    $',
    0.33
     ಮಕ್ಕಳ
    0.33
    讨
    0.33
     labours
    0.32
    POSITIVE LOGITS
     redux
    0.39
     қай
    0.37
     nuevo
    0.37
     nuovo
    0.37
     Ruby
    0.35
     kayna
    0.35
    斐
    0.35
    젹
    0.34
     діяльності
    0.34
    ദ്യ
    0.34
    Activations Density 0.007%

    No Known Activations