© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10963
    Prev
    Next
    INDEX
    Explanations

    language related to skills and tools needed for navigating career paths and professional life

    oai_token-act-pair · gemini-2.0-flash

    skills and tools

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    uxxxx
    -0.79
    expandindo
    -0.78
     intptr
    -0.72
     sinned
    -0.71
    WebElementEntity
    -0.69
     OBITUARY
    -0.69
     الحره
    -0.66
     chi̍t
    -0.62
    yarnpkg
    -0.62
    Diwedd
    -0.61
    POSITIVE LOGITS
    //});
    0.52
    ta
    0.48
     learn
    0.47
    Fair
    0.47
    <h2>
    0.46
    réhen
    0.46
    })).
    0.46
    "),
    0.44
    ."),
    0.44
     Fair
    0.44
    Activations Density 2.059%

    No Known Activations