© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15417
    Prev
    Next
    INDEX
    Explanations

    the letters r, t, c, l, g alone or in combination with other letters/symbols, mathematical expressions and lawsuit terms.

    oai_token-act-pair · gemini-2.0-flash

    code and math formulae

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     kılıf
    -0.47
     pulito
    -0.47
     superiori
    -0.47
     honte
    -0.46
     attentes
    -0.46
     trattato
    -0.44
    memoized
    -0.43
     mavi
    -0.43
     giu
    -0.43
     vérit
    -0.41
    POSITIVE LOGITS
     kasarigan
    1.04
     betweenstory
    0.63
     ExecuteAsync
    0.60
    ChildScrollView
    0.59
    afficheront
    0.58
     actionMode
    0.53
     initComponents
    0.52
    ~:
    0.52
    :✨
    0.52
     autorytatywna
    0.51
    Activations Density 16.407%

    No Known Activations