© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 2721
    Prev
    Next
    INDEX
    Explanations

    words related to elections and political processes

    oai_token-act-pair · gemini-2.0-flash

    declares

    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
     Nigerian
    -1.80
     Nigeria
    -1.77
    Nigeria
    -1.62
    Nigerian
    -1.59
     Nigerians
    -1.46
     NIGERIA
    -1.30
    niger
    -1.23
     niger
    -1.18
     Lagos
    -1.13
    Lagos
    -1.02
    POSITIVE LOGITS
    ঐ
    0.43
     Perci
    0.41
     Bulgar
    0.41
    downe
    0.41
     Dreyfus
    0.40
     overras
    0.40
    üedad
    0.40
     caloric
    0.39
     baum
    0.39
    sofa
    0.39
    Activations Density 1.705%

    No Known Activations