© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12615
    Prev
    Next
    INDEX
    Explanations

    opinionated and potentially negative descriptions of people

    oai_token-act-pair · gemini-2.0-flash

    pastry words

    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
     propOrder
    -0.86
    Jeografia
    -0.69
    ukone
    -0.61
    httphttps
    -0.60
     AssemblyCulture
    -0.60
    RegressionTest
    -0.60
     chi̍t
    -0.59
    ništ
    -0.58
     CreateTagHelper
    -0.58
    Сылтамалар
    -0.57
    POSITIVE LOGITS
     pie
    0.75
     Pie
    0.59
     pies
    0.56
    birds
    0.54
    pie
    0.54
     cakes
    0.52
    Pie
    0.52
    bags
    0.50
     birds
    0.48
    bird
    0.48
    Activations Density 0.787%

    No Known Activations