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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 2-GEMMASCOPE-TRANSCODER-16K
    4. 14247
    Prev
    Next
    INDEX
    Explanations

    parts of computer code, legal documents and scientific publications with numbers associated with each

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_2/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
    ↵
    -0.66
    '
    -0.60
      
    -0.53
     '
    -0.52
    ↵↵↵
    -0.49
    "
    -0.48
    ',
    -0.46
     "
    -0.45
    <bos>
    -0.45
        
    -0.44
    POSITIVE LOGITS
    IVEREF
    0.90
     MenuView
    0.82
    Datuak
    0.81
     >=",
    0.79
     LUMP
    0.77
    oprecipitation
    0.69
    adaptiveStyles
    0.67
     GenerationType
    0.66
     الوطنيه
    0.64
    fromnode
    0.64
    Activations Density 0.318%

    No Known Activations