© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 12-GEMMASCOPE-2-TRANSCODER-262K
    4. 139600
    Prev
    Next
    INDEX
    Explanations

    N'hésitez pas à me demander

    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_12_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
    是
    0.59
    s
    0.57
    re
    0.55
    o
    0.54
    an
    0.54
    ised
    0.53
    или
    0.50
    ila
    0.48
     από
    0.48
    حده
    0.48
    POSITIVE LOGITS
     Gipps
    0.69
     Фургала
    0.60
     Gippsland
    0.57
     clapping
    0.57
    लिप
    0.56
     любые
    0.56
     GSi
    0.55
     '['
    0.55
     ऐप्स
    0.55
     və
    0.55
    Activations Density 0.000%

    No Known Activations