© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 11011
    Prev
    Next
    INDEX
    Explanations

    phrases expressing incredulity and doubt about claims made by entities like "the state"

    oai_token-act-pair · gemini-2.0-flash

    government and politics

    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
    makeConstraints
    -0.75
    ########.
    -0.72
     nakalista
    -0.69
    WriteTagHelper
    -0.63
    findpost
    -0.63
    fromnode
    -0.63
    DockStyle
    -0.63
    AutoresizingMask
    -0.62
    Искәрмәләр
    -0.62
     Exacts
    -0.62
    POSITIVE LOGITS
     Device
    0.49
     device
    0.49
     urządzenia
    0.48
     tố
    0.48
     Dish
    0.45
     demas
    0.45
     devices
    0.44
     Devices
    0.43
    Desert
    0.43
    IfNot
    0.43
    Activations Density 0.494%

    No Known Activations