© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 147
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear in academic or legal writing, including citations, references to legal proceedings, and statistical analysis.

    oai_token-act-pair · gemini-2.0-flash

    Legal and medical texts

    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
    !("{}",
    -0.62
    bitur
    -0.60
    intenance
    -0.60
    abot
    -0.60
     IDisposable
    -0.58
    ogni
    -0.57
    وروبا
    -0.56
    Queryable
    -0.56
     inden
    -0.55
    duled
    -0.55
    POSITIVE LOGITS
    ReusableCell
    0.54
     "..\..\..\
    0.45
     preferido
    0.45
    AccessorTable
    0.43
     carottes
    0.42
    DESCRIPTOR
    0.42
     sikkert
    0.42
     preferencia
    0.41
     lunghe
    0.41
     préférence
    0.40
    Activations Density 14.246%

    No Known Activations