© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1719
    Prev
    Next
    INDEX
    Explanations

    code snippets and mathematical notation, especially when interspersed with non-code or text

    oai_token-act-pair · gemini-2.0-flash

    technical or programming terms

    np_token-act-pair-logits · gpt-4o-mini

    Code sequences

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     el
    -0.82
    UnusedPrivate
    -0.54
    Jeografia
    -0.51
    awtextra
    -0.48
    GOTREF
    -0.47
    كويكب
    -0.46
     El
    -0.45
     frattempo
    -0.45
     Elba
    -0.45
    SpringBootTest
    -0.44
    POSITIVE LOGITS
    uxley
    0.56
    новништво
    0.55
    исленность
    0.55
     MainAxisSize
    0.51
     lọc
    0.51
    AnimationsModule
    0.51
    AGAN
    0.50
    epam
    0.50
    GeneratedCode
    0.50
    dersfield
    0.50
    Activations Density 3.207%

    No Known Activations