© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10529
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to driving violations, insurance, and fines

    oai_token-act-pair · gemini-2.0-flash

    words related to traffic violations or tickets

    np_token-act-pair-logits · gpt-4o-mini

    ticket

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ThroughAttribute
    -0.83
    __.__
    -0.77
    AddTagHelper
    -0.73
     '\\;'
    -0.72
    bootstrapcdn
    -0.69
     Infórmanos
    -0.64
     doInBackground
    -0.63
     propOrder
    -0.63
     cherchés
    -0.63
    thâu
    -0.62
    POSITIVE LOGITS
     ticket
    1.20
     tickets
    1.11
    ticket
    1.06
     Ticket
    1.03
     Tickets
    0.98
     TICKET
    0.97
    Ticket
    0.94
    tickets
    0.93
    TICKET
    0.91
     ticketing
    0.87
    Activations Density 1.091%

    No Known Activations