© 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
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 2062
    Prev
    Next
    INDEX
    Explanations

    words associated with physical dimensions, modifications and attributes

    oai_token-act-pair · gemini-2.0-flash

    Width

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     widths
    -0.75
     width
    -0.72
     broad
    -0.71
    Narrow
    -0.66
     Width
    -0.66
     ширина
    -0.65
     narrow
    -0.65
     narrows
    -0.64
    宽度
    -0.63
     largura
    -0.63
    POSITIVE LOGITS
    TagMode
    0.65
    CppCodeGen
    0.60
     insuffisamment
    0.55
    وجد
    0.54
    RegressionTest
    0.51
    >>;
    0.50
     дописавши
    0.50
     bouncing
    0.50
    AntiForgeryToken
    0.49
     nakalista
    0.48
    Activations Density 19.021%

    No Known Activations