© 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. 14591
    Prev
    Next
    INDEX
    Explanations

    VA benefits and veterans

    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
     Pologne
    0.59
     distinto
    0.55
     Mortara
    0.52
    tsó
    0.49
     Corea
    0.47
    ,$$
    0.47
     м
    0.46
     До
    0.46
     interpolate
    0.46
    ۹
    0.45
    POSITIVE LOGITS
    affeine
    0.50
    лни
    0.50
    Naturally
    0.48
    ល់
    0.47
    Bed
    0.47
    ক
    0.47
    賚
    0.47
    Veter
    0.46
     usi
    0.44
    CIP
    0.44
    Activations Density 0.010%

    No Known Activations