© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14873
    Prev
    Next
    INDEX
    Explanations

    words related to computer security and online fraud

    oai_token-act-pair · gemini-2.0-flash

    code injection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    featureID
    -0.79
    Hochspringen
    -0.73
     للمعارف
    -0.73
    abstractmethod
    -0.69
    MessageTagHelper
    -0.68
    coroutines
    -0.65
    StoryboardSegue
    -0.64
     Lightboxes
    -0.62
     kaynağından
    -0.62
    GBT
    -0.61
    POSITIVE LOGITS
    FormTagHelper
    0.47
     code
    0.45
     injection
    0.43
     implant
    0.39
    setViewportView
    0.39
     chamber
    0.38
     injected
    0.37
    NOPQRST
    0.36
     Савезне
    0.36
    IsMutable
    0.36
    Activations Density 1.966%

    No Known Activations