© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1643
    Prev
    Next
    INDEX
    Explanations

    segments of legal or technical text that indicate a rejection or failure of some request or action

    oai_token-act-pair · gemini-2.0-flash

    Reporting/Stating

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    reportWebVitals
    -0.61
    erio
    -0.55
    oneofs
    -0.54
    ARTER
    -0.52
    erializer
    -0.49
    turo
    -0.48
    ilets
    -0.48
    lures
    -0.48
    τύ
    -0.47
     bluff
    -0.47
    POSITIVE LOGITS
    AnchorTagHelper
    0.60
    richTextPanel
    0.56
     évidence
    0.51
    GEBURTSDATUM
    0.50
     հղումներ
    0.47
     judiciaire
    0.46
    χρι
    0.45
     aimable
    0.45
    めに
    0.45
    ValueStyle
    0.45
    Activations Density 3.064%

    No Known Activations