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. 1597
    Prev
    Next
    INDEX
    Explanations

    content in the form of instructions

    oai_token-act-pair · gemini-2.0-flash

    requests for assistance

    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
    SceneManagement
    -0.46
    xtures
    -0.46
    ']==
    -0.45
    ]<=
    -0.43
    arrings
    -0.43
     erscheint
    -0.42
    rollable
    -0.42
    hematical
    -0.41
    xture
    -0.41
    ']>
    -0.41
    POSITIVE LOGITS
     שוליים
    0.78
    verifyException
    0.75
    ImageContext
    0.72
    ControllerAdvice
    0.71
    InjectAttribute
    0.71
    TagMode
    0.69
    
    0.69
     ActionResult
    0.68
     createState
    0.67
     isNameExpr
    0.66
    Activations Density 25.519%

    No Known Activations