© 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. 3487
    Prev
    Next
    INDEX
    Explanations

    code-related terms such as variable names, classes, functions, and file types

    oai_token-act-pair · gemini-2.0-flash

    variable and component names in programming

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

    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
    oise
    -0.54
    ENDER
    -0.51
     dirait
    -0.50
    endimiento
    -0.48
     fű
    -0.47
     Past
    -0.47
    eners
    -0.47
    zuführen
    -0.46
    ستاگرام
    -0.46
    Bedrooms
    -0.46
    POSITIVE LOGITS
    Name
    0.83
    Tikang
    0.64
     Signalez
    0.61
    MLLoader
    0.59
    name
    0.59
    enumi
    0.59
     InputDecoration
    0.58
    enumii
    0.56
    NAME
    0.56
    IContainer
    0.55
    Activations Density 3.592%

    No Known Activations