© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15323
    Prev
    Next
    INDEX
    Explanations

    multiple digits, often separated by symbols

    oai_token-act-pair · gemini-2.0-flash

    say number 3

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    下载附件
    -0.59
    WireFormatLite
    -0.57
     onlyOwner
    -0.52
     onOptions
    -0.52
     Chwiliwch
    -0.50
    MRS
    -0.48
     kasarigan
    -0.48
    yarnpkg
    -0.47
     jadx
    -0.47
    :][
    -0.47
    POSITIVE LOGITS
     Three
    0.67
     three
    0.66
    3
    0.63
    ₃
    0.61
     Drei
    0.59
    ３
    0.58
    三
    0.58
    สาม
    0.58
     trois
    0.57
     مواليد
    0.57
    Activations Density 0.280%

    No Known Activations