© 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. 14675
    Prev
    Next
    INDEX
    Explanations

    words related to systems and mathematics

    oai_token-act-pair · gemini-2.0-flash

    Information processing and sensing

    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
     usually
    -0.49
     parfois
    -0.47
     sometimes
    -0.45
    有时
    -0.44
     usein
    -0.44
    Usually
    -0.43
     rarement
    -0.42
    Occasionally
    -0.42
     occasionally
    -0.41
     oftentimes
    -0.41
    POSITIVE LOGITS
    reportWebVitals
    0.62
    Datuak
    0.57
    findpost
    0.57
    minyak
    0.56
    MigrationBuilder
    0.56
     disponibilités
    0.56
    COUVER
    0.56
    ínű
    0.54
    OGND
    0.54
     kasarigan
    0.54
    Activations Density 16.206%

    No Known Activations