© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 135115
    Prev
    Next
    INDEX
    Explanations

    oxygen and ventilation support

    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_37_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
    Surface
    0.38
    اتج
    0.37
    汰
    0.37
     permukaan
    0.36
    ூர்
    0.35
     தூ
    0.35
    ड़िया
    0.35
    atán
    0.35
    借
    0.35
    缄
    0.35
    POSITIVE LOGITS
     oxygen
    0.62
    oxygen
    0.54
     Oxygen
    0.52
    酸素
    0.52
    Oxygen
    0.50
     ऑक्सीजन
    0.47
     isol
    0.45
    氧
    0.45
     isolation
    0.43
     Isol
    0.43
    Activations Density 0.018%

    No Known Activations