© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6783
    Prev
    Next
    INDEX
    Explanations

    clauses containing conditional words regarding beliefs or moral issues, particularly in a political context

    oai_token-act-pair · gemini-2.0-flash

    Peace/religious beliefs

    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
     remove
    -0.75
     removal
    -0.72
     removing
    -0.71
     Remove
    -0.69
    remove
    -0.69
     Removing
    -0.67
     removes
    -0.65
     Removal
    -0.64
     removed
    -0.62
    Removing
    -0.61
    POSITIVE LOGITS
    +#+
    0.79
     conscientious
    0.71
    InputTagHelper
    0.65
     Conscience
    0.65
     conscience
    0.65
     Peace
    0.61
     peace
    0.60
    Peace
    0.60
    /*
    0.58
    stateProvider
    0.57
    Activations Density 1.306%

    No Known Activations