© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196810
    Prev
    Next
    INDEX
    Explanations

    the word when

    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_27_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
    cales
    0.41
     Держа
    0.41
     converted
    0.40
     increase
    0.40
    ಿಸ
    0.40
     converts
    0.40
     टाक्या
    0.39
     "<
    0.39
     convert
    0.38
     substrates
    0.38
    POSITIVE LOGITS
     પડી
    0.38
     etmek
    0.37
     बुरे
    0.37
    otek
    0.36
     dignidad
    0.35
     ALSO
    0.35
     फायदेमंद
    0.34
     وتر
    0.34
     wür
    0.34
    лянчук
    0.34
    Activations Density 0.000%

    No Known Activations