© 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. 12412
    Prev
    Next
    INDEX
    Explanations

    LaTeX code snippets, especially environments and document structure

    oai_token-act-pair · gemini-2.0-flash

    document

    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
     benefits
    -0.94
     benefited
    -0.92
     benefitted
    -0.91
     benefit
    -0.89
    Benefit
    -0.84
     Benefits
    -0.84
     benefiting
    -0.82
    Benefits
    -0.82
     Benef
    -0.81
     Benefit
    -0.80
    POSITIVE LOGITS
     transfieras
    0.73
     المعيارى
    0.71
     يتيمه
    0.69
    NOPQRST
    0.66
     getClass
    0.66
    AntiForgeryToken
    0.59
     nakalista
    0.59
    حوالہ
    0.59
    AlterField
    0.59
     useRouter
    0.58
    Activations Density 3.823%

    No Known Activations