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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 25-GEMMASCOPE-TRANSCODER-16K
    4. 6706
    Prev
    Next
    INDEX
    Explanations

    code related to vulnerability in C, specifically buffer overflows, and also some related to "System.Label" (likely Java or C#)

    oai_token-act-pair · gemini-2.0-flash

    computer code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     समीक्षाएं
    -0.65
    CloseOperation
    -0.60
    StateToProps
    -0.59
    الدراسه
    -0.57
    Inhoud
    -0.56
    cách
    -0.55
     $@
    -0.55
     betweenstory
    -0.55
    Liefs
    -0.55
    躇
    -0.54
    POSITIVE LOGITS
     religieuses
    0.56
    ContentAsync
    0.54
     giuri
    0.54
     automatiques
    0.52
     voluto
    0.49
    p
    0.49
     militaires
    0.48
     StatefulWidget
    0.47
     internationaux
    0.47
     debole
    0.47
    Activations Density 17.267%

    No Known Activations