© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4529
    Prev
    Next
    INDEX
    Explanations

    words related to historical conflicts, especially wars and battles

    oai_token-act-pair · gemini-2.0-flash

    War context

    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
    uttgart
    -0.57
     humaines
    -0.55
    aarrggbb
    -0.53
     religieuses
    -0.50
     terminé
    -0.49
     définiti
    -0.47
     âgées
    -0.47
     supérieures
    -0.47
    ValueStyle
    -0.47
    rungsseite
    -0.46
    POSITIVE LOGITS
     useParams
    0.66
    idopsis
    0.63
    onAttach
    0.59
    Thiết
    0.58
    ๆ
    0.56
     established
    0.54
     massac
    0.54
    itaine
    0.53
     abolished
    0.53
     Avi
    0.53
    Activations Density 4.911%

    No Known Activations