© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4480
    Prev
    Next
    INDEX
    Explanations

    words related to conflict, particularly those involving patents, rebellion or capture for any reason

    oai_token-act-pair · gemini-2.0-flash

    insane

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    NUMX
    -0.59
     dataSnapshot
    -0.52
    ompok
    -0.52
    medim
    -0.50
    miyorum
    -0.49
     récentes
    -0.49
    axa
    -0.47
    herself
    -0.47
    omani
    -0.47
    rådet
    -0.47
    POSITIVE LOGITS
    sizeCache
    1.02
    parsedMessage
    0.90
    EDEFAULT
    0.82
    Personensuche
    0.79
    RegressionTest
    0.76
    MigrationBuilder
    0.76
    GEBURTSDATUM
    0.76
     resourceCulture
    0.76
    QMetaType
    0.76
    MessageOf
    0.74
    Activations Density 31.545%

    No Known Activations