© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8195
    Prev
    Next
    INDEX
    Explanations

    LaTeX code and possibly also chemical formulas and diagrams.

    oai_token-act-pair · gemini-2.0-flash

    mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    脚注の使い方
    -0.64
    XmlAccessType
    -0.57
     AssemblyCompany
    -0.57
    rrggbb
    -0.57
    Diweddarwch
    -0.53
    sidemargin
    -0.51
     محفوظة
    -0.49
    pool
    -0.49
    Pool
    -0.46
     pool
    -0.45
    POSITIVE LOGITS
    nalités
    0.58
    udessa
    0.56
     such
    0.55
    EnumMember
    0.48
     solchen
    0.48
     solches
    0.48
     SwiftUI
    0.47
     للمعارف
    0.47
     solche
    0.46
    énario
    0.45
    Activations Density 1.333%

    No Known Activations