© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7370
    Prev
    Next
    INDEX
    Explanations

    words related to armed conflict and tension

    oai_token-act-pair · gemini-2.0-flash

    conflict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     conflict
    -2.47
     Conflict
    -2.19
     conflicts
    -2.17
    conflict
    -2.13
    Conflict
    -1.98
     Conflicts
    -1.95
     conflits
    -1.75
     conflicto
    -1.73
     conflit
    -1.64
    Conflicts
    -1.54
    POSITIVE LOGITS
    EDEFAULT
    0.65
     mercies
    0.65
     useContext
    0.61
    ījum
    0.58
     oprot
    0.57
     Inns
    0.57
    urangan
    0.57
     esterni
    0.57
    breadcrumbs
    0.57
    ètement
    0.56
    Activations Density 2.911%

    No Known Activations