© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11085
    Prev
    Next
    INDEX
    Explanations

    code syntax like parenthesis, numbers and dollar signs

    oai_token-act-pair · gemini-2.0-flash

    while loops

    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
     until
    -0.88
    until
    -0.82
     Until
    -0.82
    Until
    -0.81
     UNTIL
    -0.76
     till
    -0.75
     untill
    -0.72
     TILL
    -0.71
    Till
    -0.69
     Till
    -0.68
    POSITIVE LOGITS
     while
    2.13
    while
    1.92
    While
    1.62
     WHILE
    1.60
     While
    1.59
     mentre
    1.55
     whilst
    1.50
    WHILE
    1.50
     mientras
    1.49
     enquanto
    1.47
    Activations Density 0.660%

    No Known Activations