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. 16381
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to reasoning, conclusions, and summaries.

    oai_token-act-pair · gemini-2.0-flash

    thus

    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
    thâu
    -0.65
     ujednoznacz
    -0.63
     numériques
    -0.59
     professeurs
    -0.56
     متعلقه
    -0.56
    typeparam
    -0.56
     chaude
    -0.55
     intenção
    -0.53
     COMPOUND
    -0.51
     emplois
    -0.51
    POSITIVE LOGITS
    Personendaten
    0.64
    "):
    
    0.63
    $.
    
    0.55
    MigrationBuilder
    0.54
    ]^{-
    0.52
    "])
    
    0.52
    RegressionTest
    0.52
    XtraEditors
    0.50
    ()?;
    0.50
    ]$}
    0.50
    Activations Density 2.789%

    No Known Activations