© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 33751
    Prev
    Next
    INDEX
    Explanations

    math notation and sequences

    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_31_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
     six
    0.48
    になっている
    0.45
    〢
    0.41
     five
    0.41
     three
    0.40
     três
    0.40
     eight
    0.39
    双手
    0.39
    Ing
    0.39
    达成
    0.39
    POSITIVE LOGITS
    薯
    0.42
    परा
    0.41
     మె
    0.38
    妪
    0.36
     estimating
    0.35
    ˆ‚
    0.35
     разре
    0.35
     जब
    0.34
     جوئے
    0.34
    بيوتر
    0.34
    Activations Density 0.015%

    No Known Activations