© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 13416
    Prev
    Next
    INDEX
    Explanations

    Objective-C code related to UI elements or notifications

    oai_token-act-pair · gemini-2.0-flash

    selector

    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
     myſelf
    -0.78
    fillType
    -0.75
    DOCTYPE
    -0.73
    parsedMessage
    -0.72
     Theſe
    -0.70
    GraphicsUnit
    -0.70
    ObjectContext
    -0.69
     Monfieur
    -0.69
     MaterialApp
    -0.68
     AppColors
    -0.67
    POSITIVE LOGITS
     event
    0.52
     events
    0.52
    event
    0.51
    шру
    0.51
     function
    0.51
    events
    0.50
     regular
    0.49
    Recognizer
    0.49
    Events
    0.49
    Event
    0.49
    Activations Density 1.855%

    No Known Activations