© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1855
    Prev
    Next
    INDEX
    Explanations

    mentions of Microsoft software, coding/generation of data, and technical aspects of video game programming, especially related to 3D models and animation.

    oai_token-act-pair · gemini-2.0-flash

    the word "in"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     فريبيس
    -0.89
    IUrlHelper
    -0.77
    rungsseite
    -0.76
     propOrder
    -0.72
    dafx
    -0.70
     transfieras
    -0.70
    CppCodeGen
    -0.69
    Datuak
    -0.69
     mergeFrom
    -0.68
    oredCriteria
    -0.68
    POSITIVE LOGITS
     in
    1.09
     dalam
    0.78
     dans
    0.71
     trong
    0.71
     within
    0.68
    ใน
    0.67
     inside
    0.63
    dalam
    0.63
     în
    0.58
     في
    0.55
    Activations Density 2.652%

    No Known Activations