© 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. 16202
    Prev
    Next
    INDEX
    Explanations

    mentions of military service during wartime

    oai_token-act-pair · gemini-2.0-flash

    Military service

    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
     soldier
    -0.60
     GND
    -0.58
    :✨
    -0.58
    iastes
    -0.56
     soldat
    -0.56
     iſt
    -0.55
     þat
    -0.55
    ñora
    -0.54
     Jeune
    -0.54
    ंदीखरीदारी
    -0.52
    POSITIVE LOGITS
     незавершена
    0.69
    amen
    0.52
    maine
    0.52
    AnchorStyles
    0.51
    phis
    0.51
    tig
    0.50
     pescoço
    0.50
     straight
    0.49
    mib
    0.47
    براير
    0.47
    Activations Density 6.291%

    No Known Activations