© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 9269
    Prev
    Next
    INDEX
    Explanations

    words and phrases describing political actions and entities, especially those related to the United States and challenges to established power structures.

    oai_token-act-pair · gemini-2.0-flash

    corporations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     resourceCulture
    -0.82
    참고
    -0.64
     "..\..\..\
    -0.59
     AttributeSet
    -0.58
    findpost
    -0.57
     <<<<<<<<<<<<<<
    -0.57
    
    -0.54
    DockStyle
    -0.54
     createState
    -0.52
    Espèce
    -0.50
    POSITIVE LOGITS
     corporations
    1.14
     corporate
    1.10
     Corporations
    1.00
    Corpor
    0.97
     corpor
    0.96
     corporation
    0.95
    corporate
    0.92
     CORPOR
    0.91
    corpor
    0.91
     companies
    0.86
    Activations Density 2.130%

    No Known Activations