© 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-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11430
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to time, dates, and actions starting

    oai_token-act-pair · gemini-2.0-flash

    events taking effect

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     starting
    -1.76
     Starting
    -1.73
    Starting
    -1.70
     starts
    -1.67
    starting
    -1.65
     Starts
    -1.56
     beginning
    -1.55
     begins
    -1.52
     commencing
    -1.48
     STARTING
    -1.46
    POSITIVE LOGITS
     WaitForSeconds
    0.44
    AttributedString
    0.44
     SqlCommand
    0.43
    ải
    0.43
    JTextArea
    0.41
    drawSprites
    0.41
    posed
    0.41
     intérieure
    0.41
    ksin
    0.40
    eid
    0.40
    Activations Density 1.313%

    No Known Activations