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. 15-GEMMASCOPE-TRANSCODER-16K
    4. 16237
    Prev
    Next
    INDEX
    Explanations

    code or data structures.

    oai_token-act-pair · gemini-2.0-flash

    website code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_15/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
    adə
    -0.60
    bootstrapcdn
    -0.56
    protoimpl
    -0.56
    AndroidJUnit
    -0.55
    sə
    -0.55
    ConstraintMaker
    -0.54
    GEBURTSDATUM
    -0.54
    contentLoaded
    -0.51
    rith
    -0.50
     ostavi
    -0.50
    POSITIVE LOGITS
    messageInfo
    0.66
    #
    0.56
    ?>">
    0.54
    ]}"
    0.54
    ]<<"
    0.52
    statt
    0.52
     ?>">
    0.51
    SharedDtor
    0.51
    }]
    
    0.51
    }))
    
    0.50
    Activations Density 0.600%

    No Known Activations