© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 27565
    Prev
    Next
    INDEX
    Explanations

    COVID-19 pandemic

    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
    蜢
    0.39
     Driver
    0.39
     Luther
    0.38
    arine
    0.38
    ple
    0.37
    Driver
    0.37
    範
    0.36
    大的
    0.35
    apt
    0.34
    Serving
    0.34
    POSITIVE LOGITS
     infección
    0.66
     infection
    0.58
     enfermedad
    0.58
     doença
    0.58
     infections
    0.58
     malattia
    0.57
     doenças
    0.53
     infecciones
    0.53
     illness
    0.51
    infection
    0.50
    Activations Density 0.003%

    No Known Activations