© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15610
    Prev
    Next
    INDEX
    Explanations

    words that are commonly used in image captions, blog posts, or academic papers

    oai_token-act-pair · gemini-2.0-flash

    technical jargon or terms

    np_token-act-pair-logits · gpt-4o-mini

    blog article excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     autorytatywna
    -0.99
    EndGlobalSection
    -0.94
     nahilalakip
    -0.94
    SourceChecksum
    -0.87
    ]")]
    -0.85
    :✨
    -0.80
     GreatSchools
    -0.77
    oneofs
    -0.76
    PerformLayout
    -0.74
     OFDb
    -0.73
    POSITIVE LOGITS
     under
    0.50
     coucher
    0.47
    throw
    0.45
    buttonShape
    0.42
     tecnici
    0.42
     personale
    0.41
    JPanel
    0.41
     professionali
    0.40
     bandes
    0.40
     pessoais
    0.39
    Activations Density 2.951%

    No Known Activations