© 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. 224412
    Prev
    Next
    INDEX
    Explanations

    railroad system

    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
    imageId
    0.57
     трубы
    0.56
     масштаб
    0.54
    drivers
    0.54
    BS
    0.52
    digits
    0.50
    discipl
    0.49
     μ
    0.49
    consumer
    0.49
    LIMIT
    0.49
    POSITIVE LOGITS
    м
    0.64
    ý
    0.61
    م
    0.57
     engage
    0.57
    é
    0.57
    gh
    0.56
    ار
    0.55
    ди
    0.55
    ément
    0.54
    áte
    0.54
    Activations Density 0.000%

    No Known Activations