© 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. 13760
    Prev
    Next
    INDEX
    Explanations

    words strongly related to software engineering, QA, and software development, or the state of a test.

    oai_token-act-pair · gemini-2.0-flash

    test state

    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
     الحره
    -0.81
    ReusableCell
    -0.62
    LElement
    -0.60
     postIndex
    -0.58
    XPATH
    -0.57
     itſelf
    -0.57
    WebServlet
    -0.56
    SequentialGroup
    -0.56
    ovia
    -0.56
    riculture
    -0.54
    POSITIVE LOGITS
    expandindo
    0.52
    Myself
    0.52
     gyhoeddwyd
    0.51
    قایناقلار
    0.50
     Lauder
    0.47
     bonitas
    0.47
     envíos
    0.46
    ències
    0.45
    حوالہ
    0.45
    Према
    0.44
    Activations Density 44.659%

    No Known Activations