© 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
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 4597
    Prev
    Next
    INDEX
    Explanations

    the word "parking" and words related to rules

    oai_token-act-pair · gemini-2.0-flash

    parking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Tembelea
    -1.25
    '},
    
    -1.13
     متعلقه
    -1.13
    )";
    
    -1.12
    >\<^
    -1.12
    '],
    
    -1.11
    )");
    
    -1.08
     CreateTagHelper
    -1.05
    HasForeignKey
    -1.05
    MigrationBuilder
    -1.05
    POSITIVE LOGITS
    ↵
    0.90
    '
    0.88
    ↵↵
    0.87
    <bos>
    0.81
     of
    0.78
    <strong>
    0.77
    ↵↵↵
    0.73
    The
    0.69
     for
    0.69
     "
    0.68
    Activations Density 1.304%

    No Known Activations