© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7087
    Prev
    Next
    INDEX
    Explanations

    common words in the English language

    oai_token-act-pair · gemini-2.0-flash

    wine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     wine
    -2.19
     Wine
    -2.08
    Wine
    -2.06
     WINE
    -1.95
    wine
    -1.89
     wines
    -1.78
     Wines
    -1.64
     wijn
    -1.59
     vineyard
    -1.55
     winery
    -1.55
    POSITIVE LOGITS
     Burgess
    0.50
    ulipas
    0.47
     Lyra
    0.46
    довлет
    0.44
     mikä
    0.44
     Bathrooms
    0.44
     potty
    0.43
    kháu
    0.43
     šķ
    0.43
     Heller
    0.42
    Activations Density 0.633%

    No Known Activations