© 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. 16380
    Prev
    Next
    INDEX
    Explanations

    health insurance

    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
     sprawy
    0.38
     kunder
    0.38
    樸
    0.36
     tag
    0.35
    TAG
    0.35
     Tag
    0.35
    पान
    0.34
    Tag
    0.34
    ⛲
    0.34
     দোক
    0.34
    POSITIVE LOGITS
     Huxley
    0.45
     Hutchinson
    0.39
    特別な
    0.38
     hunt
    0.38
     numbered
    0.38
     Guru
    0.38
    ➁
    0.38
     belongs
    0.37
     Extra
    0.37
     Pl
    0.36
    Activations Density 0.025%

    No Known Activations