© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5659
    Prev
    Next
    INDEX
    Explanations

    the LaTeX code command "\begin{document}"

    oai_token-act-pair · gemini-2.0-flash

    document

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    HasForeignKey
    -0.59
    Ҭ
    -0.55
     opérateur
    -0.54
    arcoma
    -0.54
     Fixtures
    -0.54
    ()/
    -0.52
    ]["
    -0.52
    ophone
    -0.52
     Heels
    -0.51
    RemoveField
    -0.50
    POSITIVE LOGITS
    <bos>
    1.94
     itſelf
    0.66
     myſelf
    0.58
     himſelf
    0.53
    ViewFeatures
    0.53
    OGND
    0.52
     theſe
    0.51
    umumkan
    0.50
    MigrationBuilder
    0.50
     Paglinawan
    0.49
    Activations Density 0.140%

    No Known Activations