© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6180
    Prev
    Next
    INDEX
    Explanations

    object, ego, import

    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_40_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
     типу
    0.42
     decking
    0.41
    来店
    0.40
    瑄
    0.40
     hepatocytes
    0.40
     type
    0.39
     Type
    0.39
     trash
    0.38
     مشتر
    0.37
    촬
    0.37
    POSITIVE LOGITS
     object
    0.69
    object
    0.68
     объект
    0.60
     Object
    0.59
    Object
    0.57
     ego
    0.52
    オブジェクト
    0.50
     objeto
    0.48
     Ego
    0.47
    Objects
    0.47
    Activations Density 0.053%

    No Known Activations