© 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-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 15597
    Prev
    Next
    INDEX
    Explanations

    phrases that contain time

    oai_token-act-pair · gemini-2.0-flash

    time and dates

    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
    osoba
    -0.72
     ivelany
    -0.64
    はじめに
    -0.63
    ArrowToggle
    -0.63
    AddTagHelper
    -0.60
    بوابة
    -0.60
    Notae
    -0.58
     Consultez
    -0.58
    новниш
    -0.56
    ंदीखरीदारी
    -0.56
    POSITIVE LOGITS
     ranging
    0.84
     až
    0.79
     ranged
    0.76
     hanggang
    0.75
     ranges
    0.74
    ranging
    0.74
     till
    0.70
     hasta
    0.68
     hingga
    0.68
    until
    0.67
    Activations Density 2.020%

    No Known Activations