© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 9247
    Prev
    Next
    INDEX
    Explanations

    LaTeX markup, especially arrays and equations

    oai_token-act-pair · gemini-2.0-flash

    Code/math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Prompt
    -0.56
    ViewInit
    -0.55
    prompt
    -0.55
    phazard
    -0.54
     humaine
    -0.54
     fédéral
    -0.52
    CodeAttribute
    -0.51
     Bane
    -0.50
    Pon
    -0.50
     Prompt
    -0.50
    POSITIVE LOGITS
    <bos>
    0.56
    SharedDtor
    0.55
    ImageContext
    0.52
    帖最后由
    0.52
    thâu
    0.52
    ControllerTest
    0.50
    ftagPool
    0.50
    ))*
    0.48
    aryti
    0.48
     winner
    0.48
    Activations Density 1.707%

    No Known Activations