© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 6235
    Prev
    Next
    INDEX
    Explanations

    code-related tokens and operators like braces, parentheses, semicolons, and keywords

    oai_token-act-pair · gemini-2.0-flash

    Code syntax

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     jScrollPane
    -0.82
     StatelessWidget
    -0.81
     StatefulWidget
    -0.79
    IUrlHelper
    -0.76
     Normdatei
    -0.75
    MessageTagHelper
    -0.73
    MLLoader
    -0.73
     المعيارى
    -0.73
    mybatisplus
    -0.72
     שוליים
    -0.72
    POSITIVE LOGITS
     
    0.57
     ab
    0.51
     I
    0.50
    فحه
    0.48
     the
    0.48
     "
    0.48
     New
    0.47
     about
    0.47
     '
    0.46
     Pol
    0.45
    Activations Density 1.060%

    No Known Activations