© 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. 10024
    Prev
    Next
    INDEX
    Explanations

    words related to scientific writing expressing comparison, change, or mathematical terms

    oai_token-act-pair · 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
     EClass
    -0.68
    andExpect
    -0.60
     Wikimedijinoj
    -0.59
    SourceChecksum
    -0.57
    Personensuche
    -0.57
     незавершена
    -0.56
    AndroidJUnit
    -0.55
    pires
    -0.51
     referenties
    -0.50
     通販
    -0.50
    POSITIVE LOGITS
     as
    1.05
    随着
    1.00
    隨著
    0.88
     καθώς
    0.83
     As
    0.79
    As
    0.78
     conforme
    0.74
     medida
    0.69
    as
    0.68
     мере
    0.67
    Activations Density 2.814%

    No Known Activations