© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 0-GEMMASCOPE-TRANSCODER-16K
    4. 6419
    Prev
    Next
    INDEX
    Explanations

    the phrase "early life" or just the word "life" when it refers to someone's biography

    oai_token-act-pair · gemini-2.0-flash

    life

    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
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.90
     houſe
    -0.82
     greateſt
    -0.82
     AspNetCore
    -0.81
     itſelf
    -0.79
    TypedDataSet
    -0.78
     purpoſe
    -0.77
     foon
    -0.77
    ]--;
    -0.76
     dafs
    -0.75
    POSITIVE LOGITS
    <bos>
    1.06
     the
    0.64
    ↵↵
    0.58
     is
    0.45
     an
    0.43
    ↵
    0.41
    \
    0.41
     his
    0.40
     and
    0.40
     a
    0.40
    Activations Density 0.127%

    No Known Activations