© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7639
    Prev
    Next
    INDEX
    Explanations

    references to political and governmental systems

    oai_token-act-pair · gemini-2.0-flash

    political/societal systems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
    SharedDtor
    -0.94
    contentLoaded
    -0.75
    Искәрмәләр
    -0.75
    DeleteBehavior
    -0.74
     autorytatywna
    -0.70
     kasarigan
    -0.69
    хьтан
    -0.69
    IonicModule
    -0.63
     mouseY
    -0.63
    ANTLR
    -0.62
    POSITIVE LOGITS
    hay
    0.47
     pequ
    0.45
     peri
    0.42
    #![
    0.41
    cstdio
    0.41
     Lira
    0.40
    jin
    0.40
    PLAYING
    0.39
    FI
    0.39
    setValue
    0.39
    Activations Density 2.921%

    No Known Activations