© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 9721
    Prev
    Next
    INDEX
    Explanations

    words and phrases that appear in award announcements, elections, and competition results including winner, champion, medal, official, and declared.

    oai_token-act-pair · gemini-2.0-flash

    winners

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     winners
    -1.16
     recipients
    -1.12
     Recipient
    -1.10
     Recipients
    -1.10
     recipient
    -1.09
    Winners
    -1.06
    winners
    -1.05
     winner
    -1.03
    Recipient
    -1.03
     Winners
    -1.02
    POSITIVE LOGITS
    +#+#
    0.78
    styleUrls
    0.67
    ArgumentParser
    0.64
    LookAnd
    0.63
    queryInterface
    0.59
    ंदीखरीदारी
    0.55
    adaptiveStyles
    0.54
    ymce
    0.53
     esternos
    0.52
    曖昧さ回避
    0.52
    Activations Density 2.896%

    No Known Activations