© 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. 19-GEMMASCOPE-2-TRANSCODER-262K
    7. 210642
    Prev
    Next
    INDEX
    Explanations

    Layouts for GUI

    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_19_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
     cóm
    0.49
     ключ
    0.47
     blocking
    0.47
     shinobi
    0.47
    $?
    0.46
     identity
    0.45
     blockade
    0.44
    ビット
    0.44
     blackout
    0.44
     key
    0.44
    POSITIVE LOGITS
    ao
    0.48
     Pagination
    0.46
    BeforeText
    0.46
    exception
    0.45
    वाद
    0.44
     Linie
    0.44
    DatePicker
    0.44
     Transplantation
    0.44
     Wachstum
    0.44
    妆
    0.43
    Activations Density 0.001%

    No Known Activations