© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 81435
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and exponents

    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_0_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
    ری
    1.88
     are
    1.77
    t
    1.66
     and
    1.55
    ン
    1.35
    ن
    1.31
    _
    1.29
    s
    1.27
    CE
    1.27
    EN
    1.26
    POSITIVE LOGITS
    ב
    1.56
    ע
    1.53
    र
    1.41
    it
    1.36
    ر
    1.36
    u
    1.31
    ation
    1.30
    ir
    1.28
    ع
    1.27
    er
    1.24
    Activations Density 0.000%

    No Known Activations