© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4964
    Prev
    Next
    INDEX
    Explanations

    phrases discussing economic gaps, technical issues, and political concepts like tax

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/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.18.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
     ModelExpression
    -0.57
     Lehre
    -0.48
    SessionId
    -0.47
    JNI
    -0.46
    nofollow
    -0.46
    akterysty
    -0.46
     svi
    -0.46
    rekt
    -0.45
    lossary
    -0.45
    jaus
    -0.45
    POSITIVE LOGITS
    ValueStyle
    0.59
    principalTable
    0.57
    XmlType
    0.57
    ($__
    0.56
    webElementXpaths
    0.54
     وتسجيلات
    0.54
    LoadScene
    0.54
    IContainer
    0.54
    windowFixed
    0.54
    انجليز
    0.51
    Activations Density 1.271%

    No Known Activations