© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6265
    Prev
    Next
    INDEX
    Explanations

    snippets of code, specifically related to HTML writers, MIME headers, content and attachments

    oai_token-act-pair · gemini-2.0-flash

    := and =

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     enfans
    -0.63
     NSCoder
    -0.63
     avoient
    -0.62
    casio
    -0.60
     eccl
    -0.59
     réparation
    -0.57
     étoient
    -0.57
     venons
    -0.57
     paille
    -0.56
     giacca
    -0.56
    POSITIVE LOGITS
     continúas
    0.50
     world
    0.48
    MigrationBuilder
    0.48
    arXiv
    0.47
     manche
    0.47
    harusnya
    0.46
     steward
    0.44
     <<<<<<<<<<<<<<
    0.43
     snippetHide
    0.43
     Mill
    0.43
    Activations Density 1.840%

    No Known Activations