© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 163862
    Prev
    Next
    INDEX
    Explanations

    project

    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
    ﺒ
    0.53
     ф
    0.52
     firef
    0.50
     परिचाल
    0.47
    ן
    0.46
    ני
    0.46
     издели
    0.46
    CIO
    0.46
    곤
    0.46
    ၆
    0.46
    POSITIVE LOGITS
    ut
    0.49
    喍
    0.48
    with
    0.46
     GHz
    0.46
    ul
    0.46
     emitters
    0.46
    ोच्च
    0.45
     बिल्कुल
    0.45
    㐌
    0.44
    iaxial
    0.44
    Activations Density 0.000%

    No Known Activations