© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14962
    Prev
    Next
    INDEX
    Explanations

    mentions of Arabs and related empires, dynasties or people

    oai_token-act-pair · gemini-2.0-flash

    yy

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    InstrumentedTest
    -0.59
    czegó
    -0.56
    AxisAlignment
    -0.56
    CreateMap
    -0.54
    isContained
    -0.54
    WriteTagHelper
    -0.52
     initComponents
    -0.51
    adell
    -0.51
     ArrayAdapter
    -0.51
    genheiten
    -0.51
    POSITIVE LOGITS
    aarrggbb
    0.64
     EconPapers
    0.59
     الاطلاع
    0.52
     Tacitus
    0.52
    stylers
    0.52
    getSub
    0.51
    hando
    0.50
    QMetaType
    0.49
     discapacidad
    0.48
     chi̍t
    0.48
    Activations Density 0.844%

    No Known Activations