© 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. 3-GEMMASCOPE-TRANSCODER-16K
    4. 8777
    Prev
    Next
    INDEX
    Explanations

    verbs related to lawmaking, prohibition, or prevention

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    chante
    -0.51
     EventArgs
    -0.51
     تانيه
    -0.50
     mourir
    -0.48
     Grind
    -0.47
     Reste
    -0.46
    berte
    -0.46
    udesta
    -0.46
     zucchero
    -0.45
     RoutedEventArgs
    -0.45
    POSITIVE LOGITS
     avoid
    1.32
     avoiding
    1.31
    avoid
    1.31
     avoids
    1.23
    Avoid
    1.22
     avoided
    1.22
     AVOID
    1.20
     Avoiding
    1.20
     Avoid
    1.19
     avoidance
    1.18
    Activations Density 0.555%

    No Known Activations