© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14322
    Prev
    Next
    INDEX
    Explanations

    different kinds of code including some numerical, JSON format, and code function words.

    oai_token-act-pair · gemini-2.0-flash

    ..

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
      
    -0.86
     “
    -0.52
     extra
    -0.49
     ${
    -0.48
     by
    -0.48
     "
    -0.48
    –
    -0.46
     N
    -0.45
    a
    -0.45
    ,
    -0.45
    POSITIVE LOGITS
     itſelf
    1.02
     Chriftian
    0.98
     poffe
    0.98
     Monfieur
    0.95
    parsedMessage
    0.94
     Eſ
    0.93
     houſe
    0.90
    uxxxx
    0.89
     Reſ
    0.89
     Efq
    0.89
    Activations Density 10.418%

    No Known Activations