© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 5822
    Prev
    Next
    INDEX
    Explanations

    shortness of breath or difficulty breathing

    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_40_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
     اکرم
    0.36
     ভূ
    0.35
     grizzly
    0.34
     ইসলামী
    0.34
    णाल
    0.33
     обла
    0.33
     ಅಂತ
    0.33
     劉
    0.33
     আপ
    0.33
    acrylamide
    0.33
    POSITIVE LOGITS
     shortness
    1.52
     breath
    1.35
    breath
    1.27
    Breath
    1.23
     Breath
    1.22
     breathe
    1.11
     breathing
    1.07
    Short
    1.01
     breaths
    1.00
    呼吸
    0.99
    Activations Density 0.066%

    No Known Activations