© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12790
    Prev
    Next
    INDEX
    Explanations

    the word "wide," especially in the context of "wide range."

    oai_token-act-pair · gemini-2.0-flash

    wide

    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
    rungsseite
    -0.85
    RegressionTest
    -0.82
     defStyle
    -0.72
    MessageTagHelper
    -0.69
     ujednoznacz
    -0.67
    BufferException
    -0.65
    AddTagHelper
    -0.63
     mergeFrom
    -0.62
    NameInMap
    -0.61
     Autorizaciones
    -0.60
    POSITIVE LOGITS
     list
    0.68
     array
    0.54
     catalogue
    0.51
    Portail
    0.50
    list
    0.47
    CORD
    0.47
     rangs
    0.47
    zul
    0.47
     catalog
    0.46
     ơn
    0.45
    Activations Density 0.982%

    No Known Activations