© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 8771
    Prev
    Next
    INDEX
    Explanations

    references to Russia, Crimea, and Lithuania, especially in the context of political and military actions.

    oai_token-act-pair · gemini-2.0-flash

    Eastern Europe/Russia 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_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
     CreateTagHelper
    -0.83
     nahilalakip
    -0.73
     Мексичка
    -0.69
    +#+
    -0.66
    PickerController
    -0.61
     ivelany
    -0.61
    AddTagHelper
    -0.59
    WithIOException
    -0.58
     ModelRenderer
    -0.57
    !*\
    -0.56
    POSITIVE LOGITS
     Kh
    0.62
     Ir
    0.53
    BagLayout
    0.52
    vh
    0.51
     ky
    0.50
     Lu
    0.49
    Kh
    0.49
    buje
    0.49
     KH
    0.48
    VH
    0.47
    Activations Density 3.035%

    No Known Activations