© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4179
    Prev
    Next
    INDEX
    Explanations

    terminology related to patents and inventions

    oai_token-act-pair · gemini-2.0-flash

    skilled

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     previous
    -1.17
    previous
    -1.10
     Previous
    -1.09
    Previous
    -1.09
     PREVIOUS
    -0.97
     précédent
    -0.87
    PREVIOUS
    -0.86
     prev
    -0.83
     preceding
    -0.82
     предыду
    -0.82
    POSITIVE LOGITS
    setVerticalGroup
    0.77
    migrationBuilder
    0.69
    الإنجليزية
    0.67
    Tembelea
    0.63
    ValueStyle
    0.60
    )++;
    0.59
     typelib
    0.59
    nyttet
    0.58
     Архів
    0.58
     viewDidLoad
    0.58
    Activations Density 2.420%

    No Known Activations