© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12258
    Prev
    Next
    INDEX
    Explanations

    words related to internet and data security.

    oai_token-act-pair · gemini-2.0-flash

    security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     security
    -0.68
    Security
    -0.65
    security
    -0.64
     Security
    -0.60
    SECURITY
    -0.57
     SECURITY
    -0.54
     πρά
    -0.49
     hubieran
    -0.47
     MotionEvent
    -0.46
     australis
    -0.46
    POSITIVE LOGITS
    
    0.82
    AddHtmlAttribute
    0.81
    IsContent
    0.81
     وتسجيلات
    0.80
    DockStyle
    0.78
     سكانية
    0.77
    MemoryWarning
    0.76
    enumi
    0.70
    raszam
    0.70
    verwijspagina
    0.69
    Activations Density 1.306%

    No Known Activations