© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 261340
    Prev
    Next
    INDEX
    Explanations

    crontab -e

    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_22_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
     Петер
    0.50
    CameraOpened
    0.50
     ساعات
    0.48
     शेयरों
    0.48
     Функция
    0.46
     punctato
    0.46
    $[
    0.44
    DataAdapter
    0.43
     copiar
    0.43
     жел
    0.42
    POSITIVE LOGITS
    ’.
    0.46
    と同
    0.41
     entspre
    0.40
    隐私
    0.39
     appoints
    0.39
    欣
    0.38
    hiva
    0.38
     Nationwide
    0.38
    znego
    0.38
     Wine
    0.38
    Activations Density 0.000%

    No Known Activations