© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 16126
    Prev
    Next
    INDEX
    Explanations

    code elements such as variable names, loops, and functions related to strings, lists, and ranges

    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_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    GEBURTSDATUM
    -0.81
    ValueStyle
    -0.79
    Personensuche
    -0.69
    SpringBootTest
    -0.68
    MigrationBuilder
    -0.67
    TestingModule
    -0.65
    +:+
    -0.65
     forState
    -0.62
    expandindo
    -0.60
     QName
    -0.60
    POSITIVE LOGITS
     in
    2.00
    ใน
    1.04
     в
    1.04
     در
    1.00
     في
    0.95
     în
    0.92
     dalam
    0.92
     във
    0.78
    InThe
    0.77
     trong
    0.74
    Activations Density 1.772%

    No Known Activations