© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6728
    Prev
    Next
    INDEX
    Explanations

    C++ code snippets, especially the keywords 'friend', 'static', 'inline', and 'struct'

    oai_token-act-pair · gemini-2.0-flash

    friend

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    الحياه
    -0.85
    RenderAtEndOf
    -0.76
    ьаж
    -0.75
     estekak
    -0.75
     متعلقه
    -0.71
     NSCoder
    -0.71
    ReusableCell
    -0.71
    OrBuilder
    -0.67
    Handlung
    -0.66
     CURIAM
    -0.63
    POSITIVE LOGITS
    <bos>
    0.98
    public
    0.68
    TagMode
    0.57
     public
    0.56
    def
    0.54
    extern
    0.53
     TType
    0.48
    EXTERN
    0.47
     function
    0.47
    function
    0.46
    Activations Density 0.952%

    No Known Activations