© 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. 208755
    Prev
    Next
    INDEX
    Explanations

    you'll be

    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
     представлена
    0.35
    Microsoft
    0.33
    Би
    0.31
    ҳои
    0.31
    Russia
    0.30
     Microsoft
    0.29
     можно
    0.29
     $\{\
    0.29
    ంతి
    0.29
    いくつかの
    0.29
    POSITIVE LOGITS
     riserv
    0.34
     recital
    0.33
    سك
    0.31
     literate
    0.30
     scripture
    0.30
     temperament
    0.30
     sprites
    0.30
     prenot
    0.30
     నిర్మాత
    0.29
     protokol
    0.29
    Activations Density 0.002%

    No Known Activations