© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 89292
    Prev
    Next
    INDEX
    Explanations

    Manufacturing principles

    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_3_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
    밂
    0.63
     fidèle
    0.62
     детям
    0.61
     семей
    0.60
     świet
    0.60
     celebrar
    0.59
    جتما
    0.58
    لوب
    0.57
     lembrar
    0.57
     обеспечение
    0.56
    POSITIVE LOGITS
    v
    1.11
    '
    0.90
    p
    0.87
    j
    0.82
    и
    0.80
    é
    0.80
    ,
    0.77
    h
    0.76
    ä
    0.76
    s
    0.75
    Activations Density 0.001%

    No Known Activations