© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 10198
    Prev
    Next
    INDEX
    Explanations

    code snippets involving database operations

    oai_token-act-pair · gemini-2.0-flash

    Database code ("db")

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    db
    -2.03
     db
    -1.88
    DB
    -1.88
     DB
    -1.63
    Db
    -1.58
     Db
    -1.39
    Database
    -1.30
     Database
    -1.23
     database
    -1.21
    database
    -1.20
    POSITIVE LOGITS
     بيها
    0.58
     '\\;'
    0.57
    sement
    0.57
    didSet
    0.55
    virons
    0.54
     pacote
    0.53
    ียด
    0.53
    NodeName
    0.53
    ellem
    0.52
     ход
    0.52
    Activations Density 4.086%

    No Known Activations