© 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. 13313
    Prev
    Next
    INDEX
    Explanations

    words related to production with automated systems

    oai_token-act-pair · gemini-2.0-flash

    technology

    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
    <bos>
    -0.70
    swire
    -0.46
    ódź
    -0.45
    вочка
    -0.45
    purl
    -0.43
     Ouverture
    -0.42
    ConstraintMaker
    -0.42
     rush
    -0.42
     LUMP
    -0.40
    ://$
    -0.40
    POSITIVE LOGITS
    mybatisplus
    0.66
    wede
    0.60
    QMetaType
    0.58
     MenuView
    0.57
    gewiesen
    0.57
    onViewCreated
    0.56
    NameInMap
    0.56
    WaitGroup
    0.55
    UpInside
    0.55
    SBATCH
    0.55
    Activations Density 1.543%

    No Known Activations