© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15371
    Prev
    Next
    INDEX
    Explanations

    text from law or regulatory documents

    oai_token-act-pair · gemini-2.0-flash

    Legal/regulatory documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     esternos
    -0.59
    `;
    -0.53
    IUrlHelper
    -0.52
    Bronnen
    -0.51
    
    -0.50
     AssemblyCulture
    -0.49
    GEBURTSDATUM
    -0.49
     Autorizaciones
    -0.47
    endregion
    -0.46
    RenderAtEndOf
    -0.45
    POSITIVE LOGITS
    BufferException
    0.71
     typelib
    0.60
     useSelector
    0.56
     NBS
    0.55
     IERC
    0.55
    TestingModule
    0.54
     PPD
    0.54
     Presiding
    0.53
     habilit
    0.53
    ero
    0.52
    Activations Density 8.413%

    No Known Activations