© 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. 58977
    Prev
    Next
    INDEX
    Explanations

    nested loops

    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
    _
    0.73
     fla
    0.62
     modifier
    0.61
     decap
    0.59
     vaccinate
    0.58
     să
    0.58
     vacate
    0.58
     ö
    0.57
     lä
    0.57
    ing
    0.55
    POSITIVE LOGITS
    c
    0.72
    сс
    0.70
    ку
    0.62
    ка
    0.59
    ()*
    0.59
    ریس
    0.59
    ac
    0.58
     Czę
    0.57
     Через
    0.55
     Для
    0.55
    Activations Density 0.010%

    No Known Activations