© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4166
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols in mathematical expressions

    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_39_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
    🚅
    0.50
    笾
    0.49
    qiya
    0.44
     condominiums
    0.44
    ovod
    0.43
     کیشن
    0.42
     conject
    0.42
     ежедневно
    0.42
     православ
    0.42
    ⑨
    0.41
    POSITIVE LOGITS
     U
    0.42
     Dead
    0.40
    R
    0.39
     P
    0.39
     net
    0.38
     single
    0.37
     Ad
    0.37
     Sub
    0.37
     glitch
    0.37
    0.37
    Activations Density 0.006%

    No Known Activations