© 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. 13592
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to digital devices, technology and connectivity

    oai_token-act-pair · gemini-2.0-flash

    technology, disengagement

    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
     pinulongan
    -0.89
     שוליים
    -0.84
     betweenstory
    -0.80
     Paglinawan
    -0.76
    setVerticalGroup
    -0.76
     ExecuteAsync
    -0.73
    AndEndTag
    -0.72
     EconPapers
    -0.71
    сшта
    -0.70
    ftagPool
    -0.68
    POSITIVE LOGITS
    Deep
    0.48
    Digital
    0.48
     digital
    0.46
     Digital
    0.44
     numériques
    0.44
    ansu
    0.44
    SuppressLint
    0.44
     Récup
    0.43
    El
    0.42
     deep
    0.42
    Activations Density 0.661%

    No Known Activations