© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11725
    Prev
    Next
    INDEX
    Explanations

    words related to SQL database code and data arrays

    oai_token-act-pair · gemini-2.0-flash

    ado

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ato
    -0.97
    ado
    -0.85
    ada
    -0.81
    ATO
    -0.71
    ADO
    -0.60
    ADA
    -0.59
    ArgumentParser
    -0.56
    SBATCH
    -0.55
    Cordialement
    -0.54
    adas
    -0.53
    POSITIVE LOGITS
    <bos>
    0.91
     propOrder
    0.60
     Lorca
    0.59
     незавершена
    0.56
    ργα
    0.56
     itſelf
    0.54
     erop
    0.54
    Vorlage
    0.54
    <?
    0.53
     Telugu
    0.53
    Activations Density 2.239%

    No Known Activations