© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7951
    Prev
    Next
    INDEX
    Explanations

    words related to cyber attacks, security, and political investigations of them

    oai_token-act-pair · gemini-2.0-flash

    cyber

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    LEncoder
    -0.69
    UnusedPrivate
    -0.69
    windowFixed
    -0.68
    PerformLayout
    -0.67
    ServletException
    -0.66
    帖最后由
    -0.66
     ModelExpression
    -0.65
     MainAxisSize
    -0.62
    igshid
    -0.61
     StatelessWidget
    -0.61
    POSITIVE LOGITS
     للمعارف
    0.62
     attacco
    0.55
     attack
    0.52
     hardening
    0.52
     saldır
    0.51
     security
    0.51
     neo
    0.50
     attaques
    0.48
     cyber
    0.47
     Horizonte
    0.47
    Activations Density 1.124%

    No Known Activations