© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13434
    Prev
    Next
    INDEX
    Explanations

    references to numbered lists, parts, seasons, or steps

    oai_token-act-pair · gemini-2.0-flash

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     utafitiHapana
    -0.59
    ADVERTISEMENT
    -0.51
    WebControls
    -0.48
     Wiktionnaire
    -0.47
     little
    -0.47
    JNIEnv
    -0.47
    setcounter
    -0.47
    fxml
    -0.46
    usermodel
    -0.46
    ErrorListener
    -0.45
    POSITIVE LOGITS
    PreferredItem
    0.76
    SourceChecksum
    0.60
    DoubleQuotes
    0.58
     initComponents
    0.56
    iastes
    0.56
    úl
    0.56
     soru
    0.56
    nextPage
    0.55
    Jeografia
    0.55
    readLine
    0.54
    Activations Density 1.253%

    No Known Activations