© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2406
    Prev
    Next
    INDEX
    Explanations

    periods immediately preceeding numbers

    oai_token-act-pair · gemini-2.0-flash

    Foreign words

    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
     éprou
    -0.59
    webElement
    -0.57
     comigo
    -0.56
     >(
    -0.54
    MENAFN
    -0.54
     genitori
    -0.53
    ddar
    -0.52
     sauvages
    -0.52
     venons
    -0.51
    */),
    -0.51
    POSITIVE LOGITS
    Portale
    0.66
    بوابة
    0.65
    istani
    0.54
     ProductService
    0.52
    BindView
    0.51
     onOptions
    0.51
    gley
    0.50
    ReusableCell
    0.50
     članak
    0.50
    RequestMapping
    0.49
    Activations Density 0.161%

    No Known Activations