© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6129
    Prev
    Next
    INDEX
    Explanations

    code snippets involving parenthesis and braces

    oai_token-act-pair · gemini-2.0-flash

    Parentheses and semicolons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
    <eos>
    -0.48
    ↵↵
    -0.45
    big
    -0.43
     big
    -0.42
     //
    -0.42
     V
    -0.40
    ']);
    -0.40
    });
    -0.40
    úcar
    -0.40
    '];
    -0.39
    POSITIVE LOGITS
    MLLoader
    0.90
     JpaRepository
    0.78
     metav
    0.76
     Jefus
    0.75
     NDEBUG
    0.73
    setupUi
    0.72
     myſelf
    0.72
     ſta
    0.71
     ſever
    0.70
     uſed
    0.70
    Activations Density 1.987%

    No Known Activations