© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 4382
    Prev
    Next
    INDEX
    Explanations

    the word "the" after words indicating explanation or summary, and also has a preference for the phrase "one of the" and related phrases

    oai_token-act-pair · gemini-2.0-flash

    reason

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    IsContent
    -0.54
    ьаж
    -0.49
     altrimenti
    -0.47
     verrez
    -0.46
    cules
    -0.46
     zugesch
    -0.46
     >=",
    -0.46
     ferdig
    -0.43
     geleverd
    -0.43
     supérieures
    -0.43
    POSITIVE LOGITS
     reason
    0.80
     EconPapers
    0.71
    reason
    0.62
     reasons
    0.60
    CardBody
    0.59
     main
    0.57
     Reason
    0.57
    FormTagHelper
    0.57
    ContentAlignment
    0.57
     ragioni
    0.56
    Activations Density 2.791%

    No Known Activations