© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5067
    Prev
    Next
    INDEX
    Explanations

    passages where people are trying to convince others to take (or avoid) some action.

    oai_token-act-pair · gemini-2.0-flash

    warnings and conclusions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     crdi
    -0.60
    nosaurus
    -0.57
     AssemblyProduct
    -0.57
    SafeMath
    -0.56
     BoxFit
    -0.56
     impossível
    -0.56
     tenements
    -0.56
     bezeichneter
    -0.55
     tfsi
    -0.54
     seasonally
    -0.54
    POSITIVE LOGITS
    MigrationBuilder
    0.61
    prepareStatement
    0.52
    новниш
    0.50
    ytä
    0.49
     e
    0.45
     etc
    0.45
     u
    0.44
     pro
    0.43
    Servlet
    0.42
     ViewGroup
    0.42
    Activations Density 1.234%

    No Known Activations