© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15474
    Prev
    Next
    INDEX
    Explanations

    descriptions of computer network and technology markets, including related abbreviations and jargon

    oai_token-act-pair · gemini-2.0-flash

    technical terms and jargon in networking

    np_token-act-pair-logits · gpt-4o-mini

    technical, specific identifiers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     NgModule
    -0.69
     AssemblyVersion
    -0.69
    Hochspringen
    -0.68
    stdc
    -0.65
    참고
    -0.61
     članak
    -0.60
    脚注の使い方
    -0.56
     المعيارى
    -0.54
     StringTokenizer
    -0.53
     yyl
    -0.52
    POSITIVE LOGITS
     EconPapers
    0.59
    DockStyle
    0.56
    WriteAttribute
    0.54
    classnames
    0.49
     télévisée
    0.47
     Complex
    0.45
    ouvre
    0.45
     complex
    0.45
    ViewFeatures
    0.44
    anglès
    0.43
    Activations Density 1.118%

    No Known Activations