© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 36758
    Prev
    Next
    INDEX
    Explanations

    system dynamics, analysis, documentation

    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_3_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
    ธุ์
    0.56
    ک
    0.55
    0.55
     चाहें
    0.54
     фено
    0.53
     पर्याय
    0.53
     (
    0.52
     успо
    0.52
     unaccount
    0.50
     आंसू
    0.50
    POSITIVE LOGITS
    人
    0.87
    n
    0.79
    ной
    0.79
    ET
    0.69
    ン
    0.69
    大
    0.66
    de
    0.66
    ного
    0.64
    т
    0.63
    न
    0.63
    Activations Density 0.005%

    No Known Activations