© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124937
    Prev
    Next
    INDEX
    Explanations

    theremin or mathematical theorems

    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_3_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
    a
    1.12
    i
    0.94
    o
    0.85
    n
    0.74
    น
    0.67
    y
    0.66
    is
    0.65
    ために
    0.64
    н
    0.62
    ه
    0.60
    POSITIVE LOGITS
    ل
    0.94
    ре
    0.83
    د
    0.68
    Кра
    0.67
    itä
    0.66
    Пе
    0.66
    Ҳ
    0.66
    Е
    0.65
    IND
    0.65
     on
    0.63
    Activations Density 0.000%

    No Known Activations