© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 92450
    Prev
    Next
    INDEX
    Explanations

    night, racing, and races

    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
    P
    0.66
    with
    0.63
    OF
    0.61
    O
    0.61
    G
    0.57
    OI
    0.57
     with
    0.55
    WITH
    0.55
    وفة
    0.55
    IN
    0.54
    POSITIVE LOGITS
     রাষ্ট্রীয়
    0.61
     uscita
    0.61
    '
    0.60
     Toen
    0.59
     هیچ
    0.58
     زمانی
    0.57
     declarar
    0.56
     вывод
    0.54
     нас
    0.53
    Quién
    0.53
    Activations Density 0.000%

    No Known Activations