© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11335
    Prev
    Next
    INDEX
    Explanations

    a combination of fragments of Japanese greetings, the mention of "Earth", and strings that look like parts of years

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    sizeCache
    -0.86
     Efq
    -0.82
    webElementXpaths
    -0.82
     BrowserModule
    -0.82
    writeField
    -0.81
     Jefus
    -0.81
    WireFormatLite
    -0.80
    WebElementEntity
    -0.79
     Meksiku
    -0.77
     Anſ
    -0.76
    POSITIVE LOGITS
     الاطلاع
    0.49
     be
    0.47
     mide
    0.43
    urs
    0.43
    роятно
    0.42
     pos
    0.42
    ToProps
    0.42
      
    0.41
    ↵
    0.41
    <eos>
    0.41
    Activations Density 1.405%

    No Known Activations