© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    words often found in legal documents and court rulings

    oai_token-act-pair · gemini-2.0-flash

    court citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     /\.
    -0.63
    URLException
    -0.62
    WebVitals
    -0.59
     näky
    -0.53
    stateProvider
    -0.52
     navideños
    -0.49
     resourceCulture
    -0.49
    Ifc
    -0.47
     ferdig
    -0.47
     wikipagina
    -0.47
    POSITIVE LOGITS
     CURIAM
    1.09
    SequentialGroup
    0.96
    CppMethod
    0.94
    RegressionTest
    0.94
    fjspx
    0.89
    DockStyle
    0.85
     autorytatywna
    0.81
    FormTagHelper
    0.75
    awtextra
    0.75
     kasarigan
    0.75
    Activations Density 4.339%

    No Known Activations