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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 1626
    Prev
    Next
    INDEX
    Explanations

    phrases that occur in the context of food consumption.

    oai_token-act-pair · gemini-2.0-flash

    actions and suffixes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    fjspx
    -0.68
    pexpr
    -0.67
     Executors
    -0.67
    withIdentifier
    -0.66
    abestanden
    -0.66
     فريبيس
    -0.63
     ویکی‌پدی
    -0.62
    IntentFilter
    -0.61
     Showers
    -0.61
    ніципа
    -0.61
    POSITIVE LOGITS
     eat
    0.93
     eating
    0.91
     eaten
    0.85
    Eat
    0.82
     Eat
    0.80
     eats
    0.77
    Eating
    0.74
    吃
    0.73
     Eating
    0.72
    食
    0.70
    Activations Density 0.455%

    No Known Activations