© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3956
    Prev
    Next
    INDEX
    Explanations

    HTML tags, especially those indicating links and formatting

    oai_token-act-pair · gemini-2.0-flash

    HTML closing tags

    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
    $.}
    -0.93
     kasarigan
    -0.92
    CppMethod
    -0.89
    ViewFeatures
    -0.85
    Искәрмәләр
    -0.85
    ]};
    -0.82
    :✨
    -0.81
    Дереккөздер
    -0.81
    __]
    -0.79
    )];
    -0.79
    POSITIVE LOGITS
    '
    1.13
    <bos>
    1.05
    ’
    0.84
    s
    0.71
    S
    0.69
    1
    0.64
    A
    0.63
    (
    0.61
    `
    0.60
     osallist
    0.58
    Activations Density 0.076%

    No Known Activations