© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12254
    Prev
    Next
    INDEX
    Explanations

    memory-related terms in a computing context

    oai_token-act-pair · gemini-2.0-flash

    interrupt/kernel level

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    protoimpl
    -0.57
    المكان
    -0.51
    enumi
    -0.47
     المعيارى
    -0.47
    nonatomic
    -0.47
     lenker
    -0.46
    localctx
    -0.45
    gång
    -0.42
     ngôi
    -0.40
    ága
    -0.40
    POSITIVE LOGITS
    Бахар
    0.65
     interrupt
    0.63
    TestingModule
    0.60
    BufferException
    0.59
     interrupting
    0.57
    fromnode
    0.56
     interrupts
    0.55
     Walkover
    0.55
    ViewSet
    0.55
    entista
    0.55
    Activations Density 2.482%

    No Known Activations