© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 33836
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Fresh
    0.71
    Fresh
    0.71
     fresh
    0.68
    fresh
    0.68
     FRESH
    0.63
     fresher
    0.58
    新鮮
    0.53
    鮮
    0.51
     freshness
    0.49
    鲜
    0.48
    POSITIVE LOGITS
    किन
    0.45
    begin
    0.38
     cell
    0.38
    скія
    0.38
     किन
    0.38
    мп
    0.38
     pas
    0.38
    HP
    0.37
    klin
    0.37
     tais
    0.37
    Activations Density 0.000%

    No Known Activations