© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113851
    Prev
    Next
    INDEX
    Explanations

    Tx and subsequent transaction/technical terms

    np_acts-logits-general · gemini-2.5-flash-lite

    the abbreviation "Tx" (often representing "transaction", "Texas", "thromboxane", or other technical terms).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    s
    -6.19
    a
    -3.98
    h
    -3.61
    n
    -3.59
    m
    -3.52
    e
    -3.20
    d
    -3.05
    y
    -2.98
    o
    -2.98
    
    -2.94
    POSITIVE LOGITS
    其妙
    3.17
    讴
    2.94
    してました
    2.63
    immen
    2.63
     帶
    2.61
    韃
    2.59
    かかる
    2.58
    飚
    2.48
    しましたが
    2.45
    轰隆
    2.41
    Activations Density 0.003%

    No Known Activations