© 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. 33596
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or fractions

    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
    中间
    0.43
    ocos
    0.38
    中期
    0.38
     persistent
    0.37
    嘯
    0.37
    せた
    0.36
    aitre
    0.35
    亚马逊
    0.35
    ந்திர
    0.35
    %；
    0.35
    POSITIVE LOGITS
    ┬
    0.34
     görü
    0.33
    NATO
    0.32
     Nig
    0.32
     istek
    0.32
    \|,
    0.32
    Ol
    0.32
    тол
    0.32
     Ard
    0.31
    Nob
    0.31
    Activations Density 0.024%

    No Known Activations