© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12052
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicative of public and government jobs and service

    oai_token-act-pair · gemini-2.0-flash

    serve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    Serving
    -1.36
     serve
    -1.34
     serving
    -1.31
    serving
    -1.30
     served
    -1.27
     Serving
    -1.25
     Serve
    -1.24
     Served
    -1.23
    serve
    -1.22
     serves
    -1.22
    POSITIVE LOGITS
    :✨
    0.70
    fjspx
    0.65
    +#+#
    0.61
    WindowConstants
    0.59
    原始内容存档于
    0.59
     समीक्षाएं
    0.57
    XmlType
    0.57
     ProtoMessage
    0.57
    
    0.55
    bootstrapcdn
    0.55
    Activations Density 15.581%

    No Known Activations