© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7661
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to removing dirt and debris or contamination

    oai_token-act-pair · gemini-2.0-flash

    contaminants and allergens in air ducts

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

    dirt and germs

    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
     Paglinawan
    -0.71
     دیکھیے
    -0.71
     Мексичка
    -0.70
     nahilalakip
    -0.69
     disambiguazione
    -0.66
    sendRedirect
    -0.65
    findpost
    -0.58
    HasForeignKey
    -0.58
     PropertyChanged
    -0.58
    ScopeManager
    -0.57
    POSITIVE LOGITS
     microbes
    0.54
     loose
    0.54
    ]._
    0.52
     soils
    0.50
     cells
    0.48
     bacteria
    0.47
     germs
    0.46
     dirt
    0.46
     pathogens
    0.45
     toxins
    0.44
    Activations Density 1.426%

    No Known Activations