© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7086
    Prev
    Next
    INDEX
    Explanations

    words associated with offices or tasks done in offices

    oai_token-act-pair · gemini-2.0-flash

    papers and documents

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    MemoryWarning
    -0.77
     فريبيس
    -0.71
    帖最后由
    -0.68
    AutoScale
    -0.64
     &___
    -0.63
     Vikipedi
    -0.61
     Référence
    -0.60
    Obrázky
    -0.59
     marquées
    -0.57
    aarrggbb
    -0.56
    POSITIVE LOGITS
     papers
    1.62
     documents
    1.38
     Papers
    1.25
    papers
    1.23
     paper
    1.23
     document
    1.19
     docs
    1.18
     Paper
    1.14
    Papers
    1.13
     PAPERS
    1.11
    Activations Density 1.869%

    No Known Activations