© 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. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 138269
    Prev
    Next
    INDEX
    Explanations

    white paper/boards

    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_12_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
    вате
    0.58
     ahorro
    0.58
     preferencias
    0.56
    ете
    0.54
    зя
    0.54
    рях
    0.53
     clipart
    0.52
    쨍
    0.52
    дям
    0.52
    ДИ
    0.51
    POSITIVE LOGITS
     st
    0.58
    found
    0.54
    ob
    0.52
    reset
    0.51
    ชั้น
    0.50
     *
    0.49
    job
    0.48
     discovered
    0.47
    caliber
    0.46
    SearchCV
    0.45
    Activations Density 0.000%

    No Known Activations