© 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. 12641
    Prev
    Next
    INDEX
    Explanations

    words and phrases concerning winning or losing a competition

    oai_token-act-pair · gemini-2.0-flash

    wins and losses

    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
    InputTagHelper
    -0.54
    XmlIgnore
    -0.49
     ministre
    -0.48
    opolis
    -0.44
    physik
    -0.43
    되지
    -0.43
    licó
    -0.43
     Prud
    -0.42
     Walking
    -0.41
     خبرگزاری
    -0.41
    POSITIVE LOGITS
    <bos>
    1.52
     AssemblyTitle
    0.93
     estimés
    0.91
    DockStyle
    0.85
    uxxxx
    0.84
     EconPapers
    0.81
     kasarigan
    0.80
    ValueStyle
    0.79
    المشاركات
    0.78
     gynhyrchwyd
    0.77
    Activations Density 0.094%

    No Known Activations