© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4269
    Prev
    Next
    INDEX
    Explanations

    positive adjectives and words related to methods, importance or ways

    oai_token-act-pair · gemini-2.0-flash

    reasons or methods

    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
     Houſe
    -0.58
     replays
    -0.57
     ingrat
    -0.54
     CURLOPT
    -0.54
     kneeling
    -0.54
     Diſ
    -0.52
     FLA
    -0.52
     kneel
    -0.52
     convertView
    -0.52
     Stadium
    -0.52
    POSITIVE LOGITS
     autorytatywna
    0.68
     مشين
    0.54
    期刊论文
    0.54
    PagerAdapter
    0.50
    теризу
    0.47
    énario
    0.46
     Clubs
    0.46
    seteq
    0.46
     seno
    0.45
     geleden
    0.45
    Activations Density 1.907%

    No Known Activations