© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8083
    Prev
    Next
    INDEX
    Explanations

    the word "double" and surrounding words when numbers are also present

    oai_token-act-pair · gemini-2.0-flash

    double

    np_max-act · gemini-2.0-flash

    double

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     double
    -0.68
    tomic
    -0.59
    visiae
    -0.56
     typelib
    -0.55
    clusal
    -0.51
    chyma
    -0.50
    quatch
    -0.50
    gäng
    -0.49
     triple
    -0.49
    kijk
    -0.48
    POSITIVE LOGITS
    RepeatedField
    0.85
    IMPORTED
    0.83
    Spoljašnje
    0.82
     étoient
    0.81
     חיצוניים
    0.78
    arakhand
    0.76
    发表于
    0.76
    contentLoaded
    0.74
     avoient
    0.73
     Theſe
    0.72
    Activations Density 1.553%

    No Known Activations