© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10025
    Prev
    Next
    INDEX
    Explanations

    scientific writing that presents results, insights, suggestions, or cautions

    oai_token-act-pair · gemini-2.0-flash

    offering insight

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     متعلقه
    -1.05
     Administrativna
    -0.98
     AssemblyProduct
    -0.96
    extAlignment
    -0.94
    Tikang
    -0.89
    expandindo
    -0.88
     nahilalakip
    -0.84
    BufferException
    -0.83
     defaultstate
    -0.82
     الدولى
    -0.82
    POSITIVE LOGITS
     insight
    0.51
     a
    0.45
     valuable
    0.44
     insights
    0.44
     val
    0.40
     specific
    0.38
     {
    0.38
     er
    0.38
     more
    0.37
     "
    0.37
    Activations Density 1.842%

    No Known Activations