© 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. 10166
    Prev
    Next
    INDEX
    Explanations

    descriptions and names of foods, especially desserts

    oai_token-act-pair · gemini-2.0-flash

    food and restaurants

    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
    +#+#
    -0.89
    клопе
    -0.87
    GraphicsUnit
    -0.82
    ⓧ
    -0.82
     hasNext
    -0.82
    enderror
    -0.79
    Datuak
    -0.79
    setVerticalGroup
    -0.78
    endphp
    -0.78
    ArgsConstructor
    -0.77
    POSITIVE LOGITS
    a
    0.39
     pij
    0.38
     a
    0.36
    روی
    0.35
     shop
    0.35
    recent
    0.35
     shops
    0.35
    f
    0.34
    lorette
    0.34
     part
    0.34
    Activations Density 6.992%

    No Known Activations