Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 970
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to legal proceedings and evidence, particularly focusing on the testimony of witnesses.

    oai_token-act-pair · gemini-2.0-flash

    witness accounts

    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
    DispatchToProps
    -0.53
    owice
    -0.52
    zerw
    -0.51
    ActionCreators
    -0.50
     estimés
    -0.50
    PHONY
    -0.50
    ię
    -0.49
     Bunny
    -0.48
     demurrer
    -0.48
    /***/
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.65
     Paglinawan
    0.56
     للاسماء
    0.53
    >>();
    0.50
    intios
    0.49
    Carriera
    0.49
    Reported
    0.48
    Cyfeiriadau
    0.47
    RegressionTest
    0.46
    utilisons
    0.46
    Activations Density 1.908%

    No Known Activations