© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14150
    Prev
    Next
    INDEX
    Explanations

    Chinese characters alongside programming code

    oai_token-act-pair · gemini-2.0-flash

    likely identifying 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
    PerformLayout
    -0.73
    StoreMessageInfo
    -0.65
    sizeCache
    -0.64
    AddHtmlAttribute
    -0.62
    UnusedPrivate
    -0.62
     transférez
    -0.60
    contentLoaded
    -0.58
    BeginInit
    -0.58
     Audiodateien
    -0.57
     Monfieur
    -0.57
    POSITIVE LOGITS
    endsection
    0.51
    lhes
    0.49
    implode
    0.49
    prisma
    0.48
    bibinfo
    0.46
    我们会
    0.46
     توانید
    0.45
    러나
    0.45
     هستیم
    0.45
    iomanip
    0.45
    Activations Density 1.269%

    No Known Activations