© 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
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12664
    Prev
    Next
    INDEX
    Explanations

    email addresses and related terms, with some possible association to embedded code and some potential for mistaking other terms

    oai_token-act-pair · gemini-2.0-flash

    Code/logs with email 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
     Teil
    -0.43
     single
    -0.40
    ingle
    -0.39
     Operation
    -0.38
    tis
    -0.38
     Press
    -0.37
     ingen
    -0.37
     Ranks
    -0.36
     oils
    -0.36
    द्धि
    -0.36
    POSITIVE LOGITS
     address
    1.14
     Address
    1.04
     ADDRESS
    1.00
    rungsseite
    0.99
     addresses
    0.97
     getAddress
    0.97
    <bos>
    0.96
    //
    0.95
    Address
    0.94
    address
    0.93
    Activations Density 1.045%

    No Known Activations