© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 3864
    Prev
    Next
    INDEX
    Explanations

    text related to programming errors and web development

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'while'

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

    Code errors and messages

    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
    Not in Any Lists

    No Comments

    Negative Logits
    hallen
    -0.46
    úsculo
    -0.44
    Архівовано
    -0.44
    скому
    -0.43
    izability
    -0.43
    UnknownFields
    -0.43
    quia
    -0.43
    uges
    -0.42
     учетом
    -0.41
    ья
    -0.41
    POSITIVE LOGITS
     while
    3.28
    while
    3.05
     While
    2.55
     WHILE
    2.55
    While
    2.53
     mentre
    2.53
     mientras
    2.47
     enquanto
    2.47
     whilst
    2.42
    WHILE
    2.38
    Activations Density 2.698%

    No Known Activations