© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 3647
    Prev
    Next
    INDEX
    Explanations

    words that relate to legal or medical writing

    oai_token-act-pair · gemini-2.0-flash

    negative events

    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
     "..\..\
    -0.50
     envie
    -0.46
     vise
    -0.45
    ChildScrollView
    -0.45
    ToProps
    -0.43
    InputBorder
    -0.43
    usermodel
    -0.42
    XmlEnum
    -0.41
     atter
    -0.41
     vais
    -0.40
    POSITIVE LOGITS
    HtmlAttribute
    0.69
    rrggbb
    0.63
     насељу
    0.61
     onCancelled
    0.60
    енча
    0.60
     autorytatywna
    0.59
     BrowserModule
    0.57
     AssemblyCulture
    0.57
    DeleteBehavior
    0.57
    verifyException
    0.56
    Activations Density 15.270%

    No Known Activations