© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14719
    Prev
    Next
    INDEX
    Explanations

    references to members of the US House of Representatives (or similar titles) followed by a name

    oai_token-act-pair · gemini-2.0-flash

    Political events/politicians

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     inde
    -0.49
    om
    -0.45
    ม
    -0.45
    M
    -0.45
    iettes
    -0.42
    忧
    -0.41
    房
    -0.41
    enga
    -0.41
     hom
    -0.40
     zug
    -0.40
    POSITIVE LOGITS
    évaluateur
    0.96
     disambiguazione
    0.93
    Personensuche
    0.85
     समीक्षाओं
    0.83
     esternos
    0.83
     ModelExpression
    0.82
    EDEFAULT
    0.82
    MessageTagHelper
    0.78
    expandindo
    0.77
    IBarButtonItem
    0.73
    Activations Density 0.390%

    No Known Activations