© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 8087
    Prev
    Next
    INDEX
    Explanations

    the word "so", and sometimes other words that are near it.

    oai_token-act-pair · gemini-2.0-flash

    so

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ]")]
    -0.52
     AssemblyCulture
    -0.51
     andato
    -0.50
     שוליים
    -0.49
     برانيه
    -0.48
    diyah
    -0.47
    GNUC
    -0.46
    ttemberg
    -0.45
    umblebee
    -0.45
    runApp
    -0.45
    POSITIVE LOGITS
    脚注の使い方
    0.70
    LookAnd
    0.66
     архивлан
    0.63
     fixed
    0.62
    
    0.60
     Escu
    0.60
     виправивши
    0.60
    zzleHttp
    0.59
    WireFormatLite
    0.59
     betweenstory
    0.59
    Activations Density 1.739%

    No Known Activations