© 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. 13046
    Prev
    Next
    INDEX
    Explanations

    code snippets and related keywords

    oai_token-act-pair · gemini-2.0-flash

    characters and whitespace in code

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

    =

    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
    yntaxException
    -1.11
    ChildScrollView
    -1.09
     BoxDecoration
    -1.05
    NewUrlParser
    -1.01
     للمعارف
    -1.01
     समीक्षक
    -1.00
     étoient
    -0.99
     Theſe
    -0.99
     photolibrary
    -0.99
    rrggbb
    -0.94
    POSITIVE LOGITS
     R
    0.62
    R
    0.57
    ↵
    0.57
     
    0.56
     P
    0.56
     B
    0.55
     d
    0.54
     tra
    0.52
    ,
    0.52
    0
    0.52
    Activations Density 2.357%

    No Known Activations