© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 49298
    Prev
    Next
    INDEX
    Explanations

    pleased to announce, confirm, or report

    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_10_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
    SE
    0.85
    9
    0.82
    and
    0.78
    3
    0.77
    it
    0.76
    for
    0.76
    1
    0.76
    at
    0.75
    ur
    0.73
    OT
    0.73
    POSITIVE LOGITS
    г
    0.91
    с
    0.91
     સારું
    0.78
     eliminación
    0.73
    е
    0.73
     nhất
    0.72
    αρ
    0.71
     концентра
    0.71
    ά
    0.70
    х
    0.68
    Activations Density 0.010%

    No Known Activations