© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 46595
    Prev
    Next
    INDEX
    Explanations

    Medicaid eligibility expansions

    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_13_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
    𝑜
    0.51
     divulge
    0.49
    ウダー
    0.47
    stic
    0.46
    Movies
    0.46
     perut
    0.46
     endian
    0.46
    Driver
    0.46
    Steven
    0.45
     zdravot
    0.45
    POSITIVE LOGITS
     любую
    0.50
     UNESCO
    0.48
    a
    0.48
     空
    0.48
     C
    0.47
    nbsp
    0.47
     B
    0.47
     ")[
    0.46
     $\
    0.46
     Coal
    0.45
    Activations Density 0.000%

    No Known Activations