© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1913
    Prev
    Next
    INDEX
    Explanations

    email addresses and related terms like "email", "phone", and "invoice"

    oai_token-act-pair · gemini-2.0-flash

    email

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     صوتيه
    -0.85
    AutoScaleMode
    -0.68
    windowFixed
    -0.67
    IsContent
    -0.66
    ⓧ
    -0.65
    SequentialGroup
    -0.65
    $_['
    -0.58
     estekak
    -0.56
    varande
    -0.56
     fémin
    -0.54
    POSITIVE LOGITS
    NewGuid
    0.55
    VersionUID
    0.51
     greater
    0.49
     terminal
    0.48
    Hướng
    0.48
    coration
    0.47
    fxml
    0.46
     blur
    0.46
    LLocation
    0.46
    ServletRequest
    0.46
    Activations Density 0.129%

    No Known Activations