© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10143
    Prev
    Next
    INDEX
    Explanations

    words and ideas related to school, education, and learning

    oai_token-act-pair · gemini-2.0-flash

    financial responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     students
    -0.69
     Students
    -0.67
     campus
    -0.66
     student
    -0.64
    Campus
    -0.63
     <>",
    -0.61
     Campus
    -0.61
    Students
    -0.60
     Student
    -0.60
    campus
    -0.59
    POSITIVE LOGITS
    extAlignment
    0.60
    AllAfrica
    0.55
    DispatchToProps
    0.55
    isticated
    0.54
    quiao
    0.54
    latego
    0.53
    garmin
    0.53
    <bos>
    0.53
     Ecclesiastical
    0.52
    underscore
    0.52
    Activations Density 1.288%

    No Known Activations