© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 844
    Prev
    Next
    INDEX
    Explanations

    words related to cleaning and maintenance

    oai_token-act-pair · gemini-2.0-flash

    clean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     clean
    -2.55
    clean
    -2.36
    Clean
    -2.34
     Clean
    -2.31
     CLEAN
    -2.17
     cleans
    -1.99
    CLEAN
    -1.98
     cleaned
    -1.95
     cleanest
    -1.94
     cleaner
    -1.84
    POSITIVE LOGITS
    <thead>
    0.48
    ={`${
    0.45
    elope
    0.43
    ZONE
    0.43
     đất
    0.42
    льника
    0.40
    μως
    0.40
    AIRE
    0.40
    galo
    0.40
     trò
    0.40
    Activations Density 7.744%

    No Known Activations