© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 5732
    Prev
    Next
    INDEX
    Explanations

    mentions of war

    oai_token-act-pair · gemini-2.0-flash

    war

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    fortawesome
    -0.49
     ddelweddau
    -0.49
    adpleegd
    -0.47
    ostock
    -0.47
    arate
    -0.44
     Growth
    -0.43
    getElementById
    -0.43
    ardless
    -0.42
    lances
    -0.42
    اریخ
    -0.42
    POSITIVE LOGITS
     ISNI
    0.64
    VIAF
    0.64
    Autoritní
    0.62
    Referències
    0.60
     насељу
    0.59
    icleta
    0.58
    apimachinery
    0.57
    complexContent
    0.54
     Affiliations
    0.54
    twimg
    0.54
    Activations Density 1.190%

    No Known Activations