© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9137
    Prev
    Next
    INDEX
    Explanations

    code-related tokens, especially array/index references, `Thread`, and loop counters

    oai_token-act-pair · gemini-2.0-flash

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    RegressionTest
    -0.84
    Personensuche
    -0.75
    ChildScrollView
    -0.74
    GEBURTSDATUM
    -0.73
     StatefulWidget
    -0.73
    transQ
    -0.73
    rungsseite
    -0.71
    enumii
    -0.69
    TagMode
    -0.69
    tagHelperRunner
    -0.68
    POSITIVE LOGITS
    组件
    0.49
     betrokken
    0.47
    /**
    0.46
    Posted
    0.43
    insert
    0.43
    alyptus
    0.42
     mijne
    0.41
     aanwezig
    0.40
    Copy
    0.40
     facing
    0.40
    Activations Density 0.697%

    No Known Activations