© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 11849
    Prev
    Next
    INDEX
    Explanations

    GT cars and racing motorcycles

    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
    icide
    0.50
    PLICATION
    0.49
     seuls
    0.48
    brom
    0.48
    чных
    0.47
    Dis
    0.47
    immunity
    0.46
    V
    0.46
    igen
    0.46
    muştur
    0.46
    POSITIVE LOGITS
     WILLIAM
    0.56
    ́i
    0.55
     ನಡೆಯ
    0.55
     Марина
    0.54
     Nisha
    0.54
     Prussians
    0.53
     Hampton
    0.52
     OutputStream
    0.52
    ⸙
    0.52
     Manchester
    0.51
    Activations Density 0.000%

    No Known Activations