© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 2976
    Prev
    Next
    INDEX
    Explanations

    security injection and scripting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_5_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsuccessful
    1.46
    災害
    1.33
    ী
    1.31
     failing
    1.31
    sess
    1.20
     Ruth
    1.19
     intercepted
    1.17
     bothering
    1.16
    న
    1.16
     المتحدة
    1.15
    POSITIVE LOGITS
    ב
    1.28
    یط
    1.26
    ت
    1.23
    andin
    1.18
    том
    1.15
    tain
    1.14
    ی
    1.14
    来讲
    1.12
     então
    1.12
    
    1.12
    Activations Density 0.154%

    No Known Activations