© 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. 8765
    Prev
    Next
    INDEX
    Explanations

    mentions of the word shop, questions being asked, and graphics cards

    oai_token-act-pair · gemini-2.0-flash

    shop

    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
    SOUNDBITE
    -0.52
    odule
    -0.47
     Menge
    -0.46
     toko
    -0.44
    anje
    -0.44
     للمعارف
    -0.44
    icar
    -0.43
    MathML
    -0.43
    Proportion
    -0.43
    inkel
    -0.42
    POSITIVE LOGITS
    featureID
    0.67
    fxml
    0.64
    uidado
    0.63
    dyž
    0.61
     Administração
    0.60
    parsedMessage
    0.58
    ViewFeatures
    0.57
    transQ
    0.57
    IUrlHelper
    0.57
     softshell
    0.55
    Activations Density 1.383%

    No Known Activations