© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7084
    Prev
    Next
    INDEX
    Explanations

    text related to the Nigerian election of Muhammadu Buhari, including names and dates

    oai_token-act-pair · gemini-2.0-flash

    politics, locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.50
    toPromise
    -0.48
    oneofs
    -0.46
    SerializedSize
    -0.46
     pall
    -0.46
    VideoCapture
    -0.45
    setopt
    -0.44
    SaveChangesAsync
    -0.44
    +#+
    -0.44
    Santis
    -0.44
    POSITIVE LOGITS
    OGND
    0.67
    ABETH
    0.56
    saraba
    0.55
    igshid
    0.55
    archiviato
    0.55
    pyplot
    0.53
    Dans
    0.52
     disambiguazione
    0.52
     hồ
    0.52
    grama
    0.51
    Activations Density 0.272%

    No Known Activations