Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14956
    Prev
    Next
    INDEX
    Explanations

    technical specifications involving attachment

    oai_token-act-pair · gemini-2.0-flash

    pressure

    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
     StatefulWidget
    -0.66
     estimés
    -0.64
    PyExc
    -0.62
    fjspx
    -0.58
    PropertyChanging
    -0.55
    تقاوى
    -0.54
    ViewImports
    -0.54
    matchCondition
    -0.51
     nakalista
    -0.51
    getMenuInflater
    -0.50
    POSITIVE LOGITS
     pressure
    0.64
     Pressure
    0.62
     framing
    0.61
    Pressure
    0.58
     PRESSURE
    0.56
    framing
    0.54
     Framing
    0.54
     pressures
    0.53
    pressure
    0.53
    IBAction
    0.47
    Activations Density 0.508%

    No Known Activations