© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13586
    Prev
    Next
    INDEX
    Explanations

    mentions of people, locations, and dates, possibly related to historical records

    oai_token-act-pair · gemini-2.0-flash

    Parliament

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    յան
    -0.43
    ǎ
    -0.41
    day
    -0.39
    ifstream
    -0.39
    thè
    -0.38
     Ostra
    -0.38
    labelledby
    -0.37
    codile
    -0.37
     ver
    -0.37
    MessageTagHelper
    -0.37
    POSITIVE LOGITS
    出版年
    0.97
     AssemblyCulture
    0.92
    Rhestr
    0.82
    oredCriteria
    0.79
    parsedMessage
    0.78
    StructEnd
    0.76
    GEBURTSDATUM
    0.76
     LoggerFactory
    0.73
    ThroughAttribute
    0.71
    瘍
    0.69
    Activations Density 1.316%

    No Known Activations