© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208864
    Prev
    Next
    INDEX
    Explanations

    often referred to as

    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_20_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
    ume
    0.44
     Etienne
    0.40
     खोली
    0.38
    moon
    0.38
    canny
    0.38
    neighbours
    0.38
    严
    0.38
    ood
    0.38
    ki
    0.38
    physik
    0.37
    POSITIVE LOGITS
     lev
    0.36
     Volume
    0.35
    ಳಿಗೆ
    0.35
    中标
    0.34
    ेश्च
    0.34
     مارچ
    0.34
    LLCATS
    0.33
    牝
    0.33
    الصف
    0.33
    ゑ
    0.33
    Activations Density 0.001%

    No Known Activations