© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10523
    Prev
    Next
    INDEX
    Explanations

    paddling, flapping, pedals, strokes

    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_13_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
    r
    0.45
    ará
    0.44
    ranging
    0.44
    en
    0.43
    c
    0.43
    ('.
    0.43
    m
    0.43
    niveau
    0.41
    첼
    0.40
    unless
    0.40
    POSITIVE LOGITS
    踩
    0.50
     paddle
    0.49
     sailors
    0.48
     Payroll
    0.48
     Share
    0.47
     Sailors
    0.47
     Paddle
    0.46
     Sandals
    0.46
    漕
    0.46
     OD
    0.45
    Activations Density 0.029%

    No Known Activations