© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13840
    Prev
    Next
    INDEX
    Explanations

    the keyword "import" at the beginning of lines of code

    oai_token-act-pair · gemini-2.0-flash

    the keyword 'import' in programming contexts

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

    importing

    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
    endpush
    -0.57
    RefreshLayout
    -0.57
     bezeichneter
    -0.56
    AddTagHelper
    -0.56
    araman
    -0.54
     layui
    -0.52
    таратура
    -0.50
     ब्रेकडाउन
    -0.50
     المعيارى
    -0.50
    وردار
    -0.49
    POSITIVE LOGITS
    ölker
    0.63
     protoimpl
    0.52
     useAppContext
    0.52
    Geografie
    0.51
     crimen
    0.51
    \{\\
    0.51
     sabia
    0.50
     Pilgri
    0.50
    hawatir
    0.48
     незавершена
    0.48
    Activations Density 0.113%

    No Known Activations