© 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. 33709
    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
    ura
    0.41
     Specialties
    0.40
    碎
    0.40
    aundice
    0.39
     म्यू
    0.39
    鲟
    0.38
    ورسٹی
    0.38
     KAP
    0.38
    Stella
    0.37
     Sera
    0.37
    POSITIVE LOGITS
    ovno
    0.43
    atmos
    0.41
    Storm
    0.38
     GN
    0.38
    흙
    0.38
    GN
    0.38
     مذہ
    0.38
    multiple
    0.38
    richter
    0.38
     бога
    0.37
    Activations Density 0.000%

    No Known Activations