© 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. 14996
    Prev
    Next
    INDEX
    Explanations

    words related to washing machines and cycles

    oai_token-act-pair · gemini-2.0-flash

    Washing and laundry

    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
    entary
    -0.68
     CURIAM
    -0.63
    FILED
    -0.57
    Camping
    -0.56
    oncesto
    -0.54
     tiroirs
    -0.54
    Redraw
    -0.54
    ymce
    -0.53
    eree
    -0.53
     Camping
    -0.53
    POSITIVE LOGITS
    AddTagHelper
    0.62
    DeleteBehavior
    0.59
     machine
    0.55
     Lä
    0.52
    FormState
    0.49
     washing
    0.47
     Machine
    0.45
    bootstrapcdn
    0.44
    롯
    0.44
     controles
    0.44
    Activations Density 0.714%

    No Known Activations