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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4968
    Prev
    Next
    INDEX
    Explanations

    language related to environmental regulations or waste management

    oai_token-act-pair · gemini-2.0-flash

    regulatory terms related to waste management

    np_token-act-pair-logits · gpt-4o-mini

    waste treatment plants

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    AndEndTag
    -0.63
    ExecuteReader
    -0.62
     للمعارف
    -0.56
    rungsseite
    -0.54
     onResponse
    -0.52
    ❋
    -0.50
    RefreshLayout
    -0.49
    CodeDom
    -0.47
    UTERS
    -0.47
     Wiktionnaire
    -0.47
    POSITIVE LOGITS
    EndGlobalSection
    0.57
    EndProject
    0.57
     permit
    0.55
     plants
    0.54
    енча
    0.54
     facilities
    0.52
     समीक्षक
    0.52
    hyperref
    0.52
     utility
    0.52
     Plants
    0.52
    Activations Density 1.985%

    No Known Activations