© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4689
    Prev
    Next
    INDEX
    Explanations

    computer architecture, instructions, or hardware

    oai_token-act-pair · gemini-2.0-flash

    software/tech errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
     avoient
    -0.48
     définiti
    -0.48
     profondo
    -0.47
     étoient
    -0.47
     cópia
    -0.43
     doulou
    -0.43
    ıştı
    -0.42
     ویکی‌پدیا
    -0.42
     voyez
    -0.41
    ronpa
    -0.41
    POSITIVE LOGITS
    enumi
    0.76
     متعلقه
    0.74
    SourceChecksum
    0.69
    ChildScrollView
    0.69
    AddHtmlAttribute
    0.68
    
    0.67
    windowFixed
    0.65
    发表于
    0.65
     <=",
    0.63
    WriteBarrier
    0.62
    Activations Density 0.880%

    No Known Activations