© 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
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16782
    Prev
    Next
    INDEX
    Explanations

    web/code/markup elements

    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_15_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
    Importer
    0.55
     s
    0.55
    Copy
    0.52
     س
    0.51
    ISIS
    0.50
    الب
    0.48
    於
    0.48
    Sweep
    0.48
     स
    0.47
    𝒔
    0.47
    POSITIVE LOGITS
    $.}
    0.50
    nesium
    0.50
     wouldn
    0.48
     yearn
    0.47
    褰
    0.47
    ma
    0.46
     Mercier
    0.46
     Nazionale
    0.46
     Primo
    0.46
     kuchh
    0.46
    Activations Density 0.000%

    No Known Activations