© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    code snippets related to software development, especially those mentioning debugging, SMS, or Facebook

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word "line"

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

    lines of code

    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
    Code
    -0.83
     Code
    -0.77
     code
    -0.71
    code
    -0.69
     CODE
    -0.64
    CODE
    -0.61
     levure
    -0.56
     Codes
    -0.54
     código
    -0.54
     CODES
    -0.50
    POSITIVE LOGITS
     lines
    1.31
     line
    1.31
     Lines
    1.13
     Line
    1.13
    Line
    1.09
    lines
    1.05
    line
    1.04
     LINE
    1.04
     LINES
    1.01
    Lines
    0.98
    Activations Density 3.929%

    No Known Activations