© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 3733
    Prev
    Next
    INDEX
    Explanations

    html and email headers, potentially code related to addresses

    oai_token-act-pair · gemini-2.0-flash

    code

    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
    Negative Logits
     CWE
    -0.65
    httphttps
    -0.60
     egne
    -0.59
     unei
    -0.57
    many
    -0.57
    TintMode
    -0.56
     Magno
    -0.56
    อง
    -0.56
     tuturor
    -0.55
     many
    -0.55
    POSITIVE LOGITS
    UrlResolution
    0.73
    >");
    0.57
    gdx
    0.56
    〗
    0.55
    Revenir
    0.55
    principalColumn
    0.55
    parametrize
    0.54
    ngrx
    0.53
     neuem
    0.53
    zieży
    0.52
    Activations Density 2.523%

    No Known Activations