© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 5373
    Prev
    Next
    INDEX
    Explanations

    text discussing farms, markets, and food, particularly organic, GMO-free, and hemp-related products.

    oai_token-act-pair · gemini-2.0-flash

    Food ingredients

    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
    是啊
    -0.49
    лакти
    -0.47
    Fast
    -0.47
    τερ
    -0.45
     estimular
    -0.43
    gol
    -0.42
     Fast
    -0.42
    നി
    -0.42
    Struct
    -0.42
    anton
    -0.41
    POSITIVE LOGITS
    enumi
    0.79
     nahilalakip
    0.77
    queryInterface
    0.68
     <<<<<<<<<<<<<<
    0.66
    +:+
    0.66
    IntoConstraints
    0.65
    uttori
    0.64
     GenerationType
    0.63
    LayoutConstraint
    0.63
    ьаж
    0.61
    Activations Density 1.643%

    No Known Activations