© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2194
    Prev
    Next
    INDEX
    Explanations

    code snippets containing programming-related words

    oai_token-act-pair · gemini-2.0-flash

    code and documentation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     BoxDecoration
    -0.63
     AssemblyTitle
    -0.58
     Shells
    -0.57
     StatefulWidget
    -0.56
    
    -0.54
    GEBURTSDATUM
    -0.53
    vetrain
    -0.52
    ezy
    -0.51
     Winaray
    -0.51
    writeFieldEnd
    -0.50
    POSITIVE LOGITS
    enoch
    0.54
     Lem
    0.50
    Slf
    0.49
    ParseTree
    0.49
    ьаж
    0.49
    Precalculus
    0.45
     bio
    0.45
     narrator
    0.44
    Lem
    0.43
    addContainerGap
    0.43
    Activations Density 22.998%

    No Known Activations