© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7320
    Prev
    Next
    INDEX
    Explanations

    scientific writing about the creation and analysis of nanoparticles and chemical reactions

    oai_token-act-pair · gemini-2.0-flash

    Nanoparticle production

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     castello
    -0.47
    ⓧ
    -0.43
     sorriso
    -0.43
     giudizio
    -0.42
     noté
    -0.41
    yot
    -0.40
    setScene
    -0.40
     vecchio
    -0.39
     referência
    -0.39
    <bos>
    -0.39
    POSITIVE LOGITS
    richTextPanel
    0.87
    featureID
    0.84
    رشف
    0.78
    setVerticalGroup
    0.78
    脚注の使い方
    0.77
    IonicModule
    0.73
    Portale
    0.69
    ölkerung
    0.67
    Bioaccumulative
    0.66
     سكانية
    0.65
    Activations Density 4.791%

    No Known Activations