© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7079
    Prev
    Next
    INDEX
    Explanations

    passages about manufacturing-related processes, especially those involving transformations with heat or other chemical changes.

    oai_token-act-pair · gemini-2.0-flash

    waste disposal

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ArrowToggle
    -0.69
    LookAnd
    -0.66
     informée
    -0.64
    NewUrlParser
    -0.60
     <=",
    -0.59
    Демографія
    -0.56
    expandindo
    -0.55
    StringCopy
    -0.51
    lück
    -0.50
    новниш
    -0.50
    POSITIVE LOGITS
     waste
    1.66
     trash
    1.63
     disposal
    1.59
     garbage
    1.50
     disposing
    1.49
     Waste
    1.48
     dispose
    1.48
    waste
    1.46
     Trash
    1.45
    Waste
    1.41
    Activations Density 2.024%

    No Known Activations