© 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. 208662
    Prev
    Next
    INDEX
    Explanations

    temperature and speed

    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
    {\
    0.34
     Col
    0.31
    because
    0.31
     छ
    0.30
    with
    0.29
    竖
    0.29
    op
    0.29
    标题
    0.29
    lb
    0.28
    Боль
    0.28
    POSITIVE LOGITS
     defini
    0.35
     tos
    0.35
    ্টা
    0.35
     transonic
    0.34
     അമേ
    0.34
     AIAA
    0.33
     kys
    0.32
     ದೇಶ
    0.32
     sufr
    0.31
     پنجاب
    0.31
    Activations Density 0.002%

    No Known Activations