Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 1555
    Prev
    Next
    INDEX
    Explanations

    job adverts for nurses, and career history for people in education and technology

    oai_token-act-pair · gemini-2.0-flash

    a

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_25/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '});
    -0.56
    complexContent
    -0.49
    Lugares
    -0.45
    ])));
    -0.45
    ైన
    -0.44
    DockStyle
    -0.44
    WithIOException
    -0.44
     esternos
    -0.43
     supérieures
    -0.43
     hoofd
    -0.42
    POSITIVE LOGITS
    mybatisplus
    0.74
    RegressionTest
    0.70
     jsPsych
    0.60
     mouseClicked
    0.59
     BorderRadius
    0.59
     surla
    0.59
     founders
    0.57
     onStop
    0.57
     SwitchCompat
    0.57
    MessageOf
    0.56
    Activations Density 3.578%

    No Known Activations