© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 14329
    Prev
    Next
    INDEX
    Explanations

    web addresses or parts of web addresses

    oai_token-act-pair · gemini-2.0-flash

    /

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    -0.75
     StatefulWidget
    -0.74
    numerusform
    -0.73
    WebServlet
    -0.67
    ">//
    -0.65
     strtotime
    -0.63
     ***!
    -0.62
     ExecuteAsync
    -0.59
    ypeł
    -0.59
     StatelessWidget
    -0.58
    POSITIVE LOGITS
     varandra
    0.61
     Amérique
    0.46
     början
    0.46
     kvinnor
    0.45
     igenom
    0.43
     végét
    0.42
     rör
    0.42
    index
    0.42
     câte
    0.42
     vänner
    0.41
    Activations Density 3.315%

    No Known Activations