© 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. 12715
    Prev
    Next
    INDEX
    Explanations

    text about handling sensitive information

    oai_token-act-pair · gemini-2.0-flash

    terms related to data privacy and sensitivity

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

    sensitive

    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
     חיצוניים
    -0.71
    ItemBackground
    -0.71
    LookAnd
    -0.67
     فريبيس
    -0.65
    webdriver
    -0.59
     cleaner
    -0.58
    AutoScaleMode
    -0.57
     Cleaner
    -0.56
    initializeApp
    -0.54
    存于互联网档案馆
    -0.54
    POSITIVE LOGITS
     sensitive
    1.98
    sensitive
    1.73
     Sensitive
    1.67
    Sensitive
    1.58
     delicate
    1.45
     sensitivity
    1.43
    ensitive
    1.41
     sensi
    1.30
    敏感
    1.30
     Sensitivity
    1.27
    Activations Density 2.065%

    No Known Activations