© 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. 12083
    Prev
    Next
    INDEX
    Explanations

    mentions of Afghanistan

    oai_token-act-pair · gemini-2.0-flash

    Afghanistan conflict 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_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
     Afghan
    -0.94
     Afghanistan
    -0.92
    Afghanistan
    -0.88
     Sussex
    -0.85
     Afgan
    -0.82
     Taliban
    -0.81
     Kabul
    -0.79
    Afghan
    -0.78
     Afghans
    -0.76
     afghan
    -0.74
    POSITIVE LOGITS
    CompleteListener
    0.53
    Olvid
    0.48
    hadi
    0.48
    IsContent
    0.45
     sekali
    0.44
    omock
    0.43
     nonatomic
    0.43
    Pup
    0.43
    nonatomic
    0.43
    NIT
    0.42
    Activations Density 2.673%

    No Known Activations