© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9180
    Prev
    Next
    INDEX
    Explanations

    words describing international relations, especially during conflict

    oai_token-act-pair · gemini-2.0-flash

    global issues and crises

    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
    verwijspagina
    -0.83
    ISupport
    -0.69
     snippetHide
    -0.68
     mapStateToProps
    -0.68
    Personensuche
    -0.64
     Paglinawan
    -0.63
     تضيفلها
    -0.61
     disambiguazione
    -0.61
    RegressionTest
    -0.61
    IsMutable
    -0.61
    POSITIVE LOGITS
    ocide
    0.60
     poly
    0.52
    quirrels
    0.45
    omitempty
    0.45
     ошибки
    0.44
    Unchecked
    0.44
    arithmic
    0.43
    ellery
    0.43
    KommentareTeilen
    0.42
    WindowManager
    0.42
    Activations Density 4.137%

    No Known Activations