© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 208376
    Prev
    Next
    INDEX
    Explanations

    epsilon in mathematical formulas

    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_20_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
     右利き
    0.45
     Δ
    0.45
     বিখ্যাত
    0.43
     ቫ
    0.43
    γεν
    0.43
     ∈
    0.42
     Muhammad
    0.41
     뛰어
    0.41
     multicolor
    0.41
     복
    0.41
    POSITIVE LOGITS
    arlene
    0.52
     sewn
    0.46
    relle
    0.46
    Sew
    0.46
    Scenes
    0.46
    ناه
    0.46
    
    0.46
     கூட
    0.45
    trombone
    0.45
    elands
    0.43
    Activations Density 0.000%

    No Known Activations