© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2682
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to confidentiality, information or disclosure

    oai_token-act-pair · gemini-2.0-flash

    secrecy/leaks

    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
    NSNotification
    -0.63
    ViewImports
    -0.59
     Confidential
    -0.55
     InputDecoration
    -0.55
    RectangleBorder
    -0.55
    apimachinery
    -0.54
     disclosing
    -0.52
    #
    -0.51
     disclosure
    -0.51
     confidential
    -0.50
    POSITIVE LOGITS
     Insee
    0.69
    Népesség
    0.56
    verifyException
    0.53
    :✨
    0.52
     noDo
    0.51
     correctes
    0.51
     Zoo
    0.49
    hoeddwyd
    0.48
     responsabili
    0.47
    RegistryLite
    0.47
    Activations Density 55.378%

    No Known Activations