© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 16765
    Prev
    Next
    INDEX
    Explanations

    sensor

    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_34_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
    育成
    0.43
     ylab
    0.40
    κλη
    0.39
    搾
    0.39
    ModelAdmin
    0.37
     setTodos
    0.36
     currentWeather
    0.35
    蟒
    0.35
    ouncement
    0.35
    架构
    0.35
    POSITIVE LOGITS
     sensors
    0.59
    センサー
    0.58
     дат
    0.57
     Sensors
    0.55
    传感器
    0.54
     sensor
    0.53
     sensores
    0.52
     Sensor
    0.51
    传感
    0.50
     sens
    0.50
    Activations Density 0.034%

    No Known Activations