© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12859
    Prev
    Next
    INDEX
    Explanations

    words suggesting a position at an extreme on a vertical axis, particularly "top" and "bottom," and potentially related words in some contexts.

    oai_token-act-pair · gemini-2.0-flash

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     top
    -3.08
    top
    -2.64
    Top
    -2.56
     Top
    -2.50
    TOP
    -2.19
     TOP
    -2.16
     tops
    -2.06
    tops
    -1.94
    トップ
    -1.84
    getTop
    -1.77
    POSITIVE LOGITS
     AssemblyCulture
    1.06
    aarrggbb
    0.79
     onOptions
    0.69
    AxisAlignment
    0.68
    expandindo
    0.68
    astéroïdes
    0.62
     BorderRadius
    0.61
     bArr
    0.60
     مرئيه
    0.60
     Numerade
    0.59
    Activations Density 5.894%

    No Known Activations