© 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-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15543
    Prev
    Next
    INDEX
    Explanations

    Azure App Service plan-related keywords, particularly when discussing virtual machines and instances

    oai_token-act-pair · gemini-2.0-flash

    Azure/Microsoft 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_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    htë
    -0.53
     AssemblyTitle
    -0.53
    Activator
    -0.47
     gift
    -0.45
    migrationBuilder
    -0.43
     contextLoads
    -0.43
    ereich
    -0.43
     cref
    -0.42
    HttpHeaders
    -0.42
     Cort
    -0.40
    POSITIVE LOGITS
     Roskov
    0.68
    AddTagHelper
    0.61
    ագրություններ
    0.60
    writeField
    0.58
    Geografía
    0.56
    WireFormatLite
    0.55
    ؤلاء
    0.54
     Sequencing
    0.54
    propylene
    0.53
    HasAnnotation
    0.52
    Activations Density 1.624%

    No Known Activations