© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13601
    Prev
    Next
    INDEX
    Explanations

    words related to stool or urine specimen collection

    oai_token-act-pair · gemini-2.0-flash

    bodily waste

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Искәрмәләр
    -0.70
     ویکی‌پدیا
    -0.61
     tribus
    -0.60
     spirituale
    -0.60
    sert
    -0.59
     cardíaca
    -0.58
    WriteTagHelper
    -0.58
     الرياضيه
    -0.57
     referenties
    -0.57
     تانيه
    -0.55
    POSITIVE LOGITS
     waste
    1.02
     poop
    1.00
     defec
    0.99
     poo
    0.92
     excre
    0.85
     feces
    0.82
     rubbish
    0.81
     dump
    0.81
     trash
    0.80
     Waste
    0.79
    Activations Density 1.705%

    No Known Activations