© 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. 12804
    Prev
    Next
    INDEX
    Explanations

    code snippets or questions/answers related to programming issues, especially within the context of Maven and Java

    oai_token-act-pair · gemini-2.0-flash

    terms related to errors or exceptions

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

    Likely detecting 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
     StatelessWidget
    -0.69
    tagHelperRunner
    -0.66
    expandindo
    -0.65
    SharedDtor
    -0.52
    kool
    -0.52
     StatefulWidget
    -0.50
     ||=
    -0.50
     courbe
    -0.49
     ivelany
    -0.48
    Datuak
    -0.47
    POSITIVE LOGITS
     تضيفلها
    0.65
    +:+
    0.58
    WebpackPlugin
    0.57
    الإنجليزية
    0.57
    InvalidProtocol
    0.56
    PullParser
    0.55
     what
    0.54
    ItemBackground
    0.53
    TintMode
    0.53
    CastException
    0.52
    Activations Density 0.562%

    No Known Activations