© 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. 4136
    Prev
    Next
    INDEX
    Explanations

    email addresses and email-related terms in multiple languages

    oai_token-act-pair · gemini-2.0-flash

    addresses

    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
    expandindo
    -0.69
     sebagainya
    -0.52
     côtés
    -0.51
     Wilhel
    -0.50
    Continued
    -0.50
     copertina
    -0.49
    æng
    -0.49
    mergeFrom
    -0.49
     diamants
    -0.48
    హ
    -0.48
    POSITIVE LOGITS
     email
    1.09
    Email
    1.02
     EMAIL
    1.01
    email
    0.99
     Email
    0.99
     emails
    0.96
    EMAIL
    0.95
     Emails
    0.92
     emailing
    0.90
     getEmail
    0.88
    Activations Density 1.214%

    No Known Activations