© 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. 10403
    Prev
    Next
    INDEX
    Explanations

    discourse markers and sentence delimiters

    oai_token-act-pair · gemini-2.0-flash

    Uncertainty

    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
    Not in Any Lists

    No Comments

    Negative Logits
    RegressionTest
    -0.66
     onCancelled
    -0.65
     дописавши
    -0.65
    
    -0.64
     disponibilités
    -0.64
    imageshack
    -0.63
    astéroïdes
    -0.63
    SBATCH
    -0.63
    contentLoaded
    -0.63
     consecration
    -0.62
    POSITIVE LOGITS
     Perhaps
    0.57
     Probably
    0.51
     Maybe
    0.50
     menj
    0.50
    Perhaps
    0.48
    perhaps
    0.47
     perhaps
    0.47
    astify
    0.46
    maybe
    0.46
     étrangères
    0.45
    Activations Density 2.470%

    No Known Activations