© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6052
    Prev
    Next
    INDEX
    Explanations

    words associated with businesses.

    oai_token-act-pair · gemini-2.0-flash

    Names

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Overhead
    -0.54
     tabernacle
    -0.53
     overhead
    -0.52
    uría
    -0.52
    EnableWeb
    -0.52
     بيها
    -0.51
    ernalia
    -0.49
    Servlet
    -0.48
     Humberto
    -0.48
     vuitton
    -0.48
    POSITIVE LOGITS
     Simon
    0.81
    Simon
    0.73
     nahilalakip
    0.72
     Graham
    0.70
     Colin
    0.69
     Nigel
    0.69
     kaarangay
    0.66
    Colin
    0.66
    Nigel
    0.65
     Ian
    0.65
    Activations Density 3.064%

    No Known Activations