© 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. 12210
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'bowl' sometimes in the context of groups of people doing something together

    oai_token-act-pair · gemini-2.0-flash

    bowl

    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
    (
    -0.72
    ↵
    -0.71
    using
    -0.69
    o
    -0.65
    er
    -0.65
    （
    -0.64
    1
    -0.64
    etCode
    -0.62
    check
    -0.62
    T
    -0.60
    POSITIVE LOGITS
    >\<^
    1.09
    Tikang
    1.05
    ^(@)
    1.03
    )";
    1.03
    )");
    0.94
    ()")
    0.93
    BibitemShut
    0.92
    ]";
    0.91
    NUMX
    0.90
    &
    0.89
    Activations Density 1.195%

    No Known Activations