© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11163
    Prev
    Next
    INDEX
    Explanations

    uses of the word "this" and "that" to refer to an abstract idea

    oai_token-act-pair · gemini-2.0-flash

    This/That

    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
    RegressionTest
    -0.47
    matchCondition
    -0.42
     Paglinawan
    -0.41
    WebServlet
    -0.40
    expandindo
    -0.39
    urlencoded
    -0.39
    AdapterFactory
    -0.39
     Infórmanos
    -0.39
    LayoutStyle
    -0.38
     же
    -0.38
    POSITIVE LOGITS
     initComponents
    0.68
     مشين
    0.62
    ."],
    0.62
    quedas
    0.60
     مؤرشف
    0.60
     combineReducers
    0.60
    存于互联网档案馆
    0.59
    RUnlock
    0.59
    Hochspringen
    0.59
    הערות
    0.58
    Activations Density 0.747%

    No Known Activations