© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 13937
    Prev
    Next
    INDEX
    Explanations

    lists of food items, especially unhealthy snacks

    oai_token-act-pair · gemini-2.0-flash

    Potato chips

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     AssemblyProduct
    -0.96
    AnchorStyles
    -0.89
    :✨
    -0.83
    MigrationBuilder
    -0.81
    StoryboardSegue
    -0.81
    TintMode
    -0.78
    تقاوى
    -0.77
    ConstraintMaker
    -0.77
    DockStyle
    -0.76
    CodeAttribute
    -0.76
    POSITIVE LOGITS
     F
    0.82
     chips
    0.55
    F
    0.52
     M
    0.50
     chip
    0.48
     Ruff
    0.48
     Lay
    0.48
     L
    0.47
     f
    0.47
    ays
    0.47
    Activations Density 1.454%

    No Known Activations