© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 50115
    Prev
    Next
    INDEX
    Explanations

    Olympic events and related historical figures

    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_31_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
     Ré
    0.42
     Pil
    0.41
     Slaughter
    0.40
    噹
    0.40
     Bast
    0.38
     Slide
    0.38
     Melissa
    0.37
    ?\\
    0.37
    Bart
    0.37
    క్స్
    0.37
    POSITIVE LOGITS
     coronation
    0.46
     ओलंपिक
    0.43
     демонстра
    0.41
     두고
    0.40
     annotate
    0.39
     Olympic
    0.37
     isolate
    0.37
     दुनियाभर
    0.36
     빌
    0.36
     olímp
    0.36
    Activations Density 0.008%

    No Known Activations