© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 164725
    Prev
    Next
    INDEX
    Explanations

    conference, practical, forum, catalog

    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_13_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
     contoh
    0.45
     parâmetros
    0.44
     сильно
    0.43
    <0xB3>
    0.43
    টসঅ্যাপ
    0.42
    టువంటి
    0.42
    ссив
    0.41
     soulful
    0.41
     прикла
    0.41
     காவல்
    0.40
    POSITIVE LOGITS
    GE
    0.52
    Report
    0.50
    Forest
    0.49
    REPORT
    0.48
    One
    0.46
    רו
    0.46
    War
    0.46
    ك
    0.46
    LE
    0.46
    ING
    0.46
    Activations Density 0.001%

    No Known Activations