© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12490
    Prev
    Next
    INDEX
    Explanations

    mentions of Nigeria and related locations or ethnicities

    oai_token-act-pair · gemini-2.0-flash

    Nigeria

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Nigeria
    -1.30
     Nigerian
    -1.16
    Nigeria
    -1.13
    Nigerian
    -0.98
     Nigerians
    -0.96
     NIGERIA
    -0.93
     niger
    -0.82
     Ghana
    -0.82
     Lagos
    -0.80
    Lagos
    -0.75
    POSITIVE LOGITS
     Audiodateien
    0.69
     ControllerBase
    0.64
    MLLoader
    0.61
     digress
    0.60
    其妙
    0.59
    unyai
    0.59
    appliquer
    0.58
     scoops
    0.57
    transQ
    0.57
     Numerade
    0.56
    Activations Density 1.625%

    No Known Activations