© 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. 15926
    Prev
    Next
    INDEX
    Explanations

    the word "up"

    oai_token-act-pair · gemini-2.0-flash

    up

    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
    ⓧ
    -0.80
    RegressionTest
    -0.78
    inaldi
    -0.73
     CreateTagHelper
    -0.71
    Rüyada
    -0.70
    Carriera
    -0.70
    PerformLayout
    -0.66
    SharedDtor
    -0.65
     otomatig
    -0.63
     comuniques
    -0.60
    POSITIVE LOGITS
     leetcode
    0.54
    stdc
    0.48
     homotopy
    0.41
     larmes
    0.41
     Zier
    0.39
    gr
    0.39
     BoxDecoration
    0.39
    dat
    0.39
     gestes
    0.38
     investissements
    0.38
    Activations Density 0.590%

    No Known Activations