© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59389
    Prev
    Next
    INDEX
    Explanations

    title or títulos

    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_11_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
    ﺶ
    0.62
     caring
    0.57
     کتاب
    0.56
    ڑا
    0.55
    加え
    0.55
    رے
    0.54
     ಪಕ್ಷ
    0.54
    نٹ
    0.54
    ﻦ
    0.54
    ﮏ
    0.54
    POSITIVE LOGITS
    2
    0.71
    4
    0.70
    3
    0.65
     Have
    0.64
     {
    0.57
    Button
    0.56
    5
    0.55
     Canucks
    0.55
    hon
    0.54
     have
    0.53
    Activations Density 0.001%

    No Known Activations