© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 15047
    Prev
    Next
    INDEX
    Explanations

    terms related to nuclear weapons and international conflict

    oai_token-act-pair · gemini-2.0-flash

    nuclear weapons and threats

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    endphp
    -0.56
     ostavi
    -0.54
    webElementXpaths
    -0.53
     Meksiku
    -0.52
     Infórmanos
    -0.50
    Fernsehserie
    -0.49
    日閲覧
    -0.49
    nele
    -0.47
    plotlib
    -0.47
    tanleria
    -0.47
    POSITIVE LOGITS
    ChildScrollView
    0.65
     تضيفلها
    0.63
    ArgumentParser
    0.55
    ViewFeatures
    0.53
     CommandType
    0.51
    Bacter
    0.48
    urlencoded
    0.47
     énergie
    0.47
     Apostles
    0.46
     Socialist
    0.46
    Activations Density 7.423%

    No Known Activations