© 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. 32817
    Prev
    Next
    INDEX
    Explanations

    wind and weather events

    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
     reply
    0.40
    Trace
    0.39
    sphere
    0.38
    reply
    0.37
     Reply
    0.37
    StopTime
    0.37
    回复
    0.37
    追
    0.37
     আত্মসম
    0.36
    排列
    0.36
    POSITIVE LOGITS
     النموذج
    0.38
     پوست
    0.38
    輙
    0.38
     ratios
    0.37
     кожу
    0.37
    ({"
    0.35
     высота
    0.34
     풍
    0.34
     விகி
    0.33
     lớn
    0.33
    Activations Density 0.011%

    No Known Activations