© 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. 13398
    Prev
    Next
    INDEX
    Explanations

    numeric strings and percentage symbols

    oai_token-act-pair · gemini-2.0-flash

    Numbers, especially with zeros

    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
    nalités
    -0.57
     gainera
    -0.56
    cticut
    -0.54
     initComponents
    -0.54
    تقاوى
    -0.53
     Dalio
    -0.50
     незавершена
    -0.49
    rzost
    -0.49
    وفاته
    -0.49
    Билгалдахарш
    -0.48
    POSITIVE LOGITS
     Anſ
    0.60
     ProgressDialog
    0.56
     tiết
    0.51
    IntoConstraints
    0.48
     Eup
    0.48
    يميديا
    0.48
    aronder
    0.47
    Eup
    0.47
     fusca
    0.47
     reaſon
    0.47
    Activations Density 23.966%

    No Known Activations