© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9953
    Prev
    Next
    INDEX
    Explanations

    the word "double"

    oai_token-act-pair · gemini-2.0-flash

    double

    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
    Билгалдахарш
    -0.77
    blurRadius
    -0.65
    RegistryLite
    -0.63
    sikker
    -0.59
     leaſt
    -0.59
    adaptiveStyles
    -0.57
     marins
    -0.56
     chromat
    -0.55
    rådet
    -0.54
    tonode
    -0.54
    POSITIVE LOGITS
    Personendaten
    0.56
    Sucesor
    0.50
     minOccurs
    0.49
    клопе
    0.47
    (&:
    0.46
    Portály
    0.46
    hysema
    0.45
    Rptr
    0.44
    省市镇
    0.44
    )|^{
    0.43
    Activations Density 0.749%

    No Known Activations