© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26
    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 14104
    Prev
    Next
    INDEX
    Explanations

    instances of people being responsible for something (or not)

    oai_token-act-pair · gemini-2.0-flash

    responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    UserScript
    -1.09
     للمعارف
    -0.97
     ©️
    -0.93
    OrNil
    -0.91
     propOrder
    -0.90
    enterOuterAlt
    -0.90
     natale
    -0.89
    NOPQRST
    -0.88
     Refugees
    -0.88
    labour
    -0.85
    POSITIVE LOGITS
     '
    
    0.90
     ")
    
    0.85
     $_"
    0.81
     ')
    
    0.81
    .",
    
    0.78
    .")
    
    0.77
     ་་
    0.77
    ']
    
    0.76
    "]
    
    0.76
    .";
    
    0.75
    Activations Density 1.162%

    No Known Activations