© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 4006
    Prev
    Next
    INDEX
    Explanations

    names and terms related to a specific historical conflict in the Middle East

    oai_token-act-pair · gemini-2.0-flash

    specific names or entities related to cultural or historical contexts

    np_token-act-pair-logits · gpt-4o-mini

    Historical figures and titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    initComponents
    -0.54
     vPvB
    -0.54
    Referències
    -0.52
     externi
    -0.50
    RegressionTest
    -0.50
    Scénario
    -0.49
    Demografia
    -0.49
     eventdata
    -0.48
    צע
    -0.47
     Vile
    -0.46
    POSITIVE LOGITS
    enumi
    0.66
    CloseOperation
    0.57
    ScopeManager
    0.55
    "}")
    0.55
    الإنجليزية
    0.54
    SuppressMessage
    0.51
    symmetry
    0.50
    Basel
    0.48
     عک
    0.48
    حال
    0.48
    Activations Density 0.737%

    No Known Activations