© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 8700
    Prev
    Next
    INDEX
    Explanations

    references to figures and patents

    oai_token-act-pair · gemini-2.0-flash

    Patents and technical 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_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
     виправивши
    -0.86
    Tembelea
    -0.80
    \{\\
    -0.79
    تقاوى
    -0.79
     الحره
    -0.77
    abestanden
    -0.75
    expandindo
    -0.75
     utafitiHapana
    -0.73
    DoubleQuotes
    -0.73
    AddHtmlAttribute
    -0.73
    POSITIVE LOGITS
    art
    0.48
    ByteString
    0.46
     čase
    0.43
    arte
    0.43
    RE
    0.43
    re
    0.43
     Aktual
    0.43
    uty
    0.42
     Re
    0.42
    zahlen
    0.42
    Activations Density 1.530%

    No Known Activations