© 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. 12072
    Prev
    Next
    INDEX
    Explanations

    words or phrases of varied context that are technical or academic

    oai_token-act-pair · 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
    FTFY
    -1.82
    unisex
    -1.77
    aquarium
    -1.74
    mountains
    -1.73
    toddler
    -1.70
    conspiracy
    -1.66
    underwater
    -1.66
    grunge
    -1.63
    predator
    -1.63
    sailor
    -1.62
    POSITIVE LOGITS
    The
    1.16
    “
    1.10
    <strong>
    1.04
    for
    1.04
    In
    0.99
    com
    0.99
    from
    0.98
    <em>
    0.97
    by
    0.96
    n
    0.95
    Activations Density 6.239%

    No Known Activations