© 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
    2. Gemma-3-27B-IT
    3. 11-GEMMASCOPE-2-TRANSCODER-262K
    4. 59296
    Prev
    Next
    INDEX
    Explanations

    check followed by specific words

    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
    颗
    0.62
     पड़ने
    0.57
    条件下
    0.57
    :“
    0.56
     ریکارڈ
    0.55
     层
    0.55
    скім
    0.54
     الد
    0.54
     attributable
    0.54
     zusätzlichen
    0.54
    POSITIVE LOGITS
    emia
    0.58
    ने
    0.55
     A
    0.55
    arenko
    0.54
    af
    0.54
    ní
    0.54
     strana
    0.53
     keinginan
    0.53
    lar
    0.51
    OLA
    0.51
    Activations Density 0.013%

    No Known Activations