© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13888
    Prev
    Next
    INDEX
    Explanations

    words and phrases about medical issues specifically related to infection control and alcohol use.

    oai_token-act-pair · gemini-2.0-flash

    wash/washing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     spreader
    -0.76
     spread
    -0.73
     contact
    -0.72
    spread
    -0.65
     contacts
    -0.64
     spreads
    -0.64
     spreading
    -0.58
    contact
    -0.58
    Contact
    -0.55
     supers
    -0.55
    POSITIVE LOGITS
    DeleteBehavior
    0.56
     wash
    0.53
     washing
    0.50
    Wash
    0.50
     washed
    0.48
     Wash
    0.47
     nahilalakip
    0.47
    ymce
    0.47
    EDEFAULT
    0.47
     Washing
    0.47
    Activations Density 1.228%

    No Known Activations