© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 218
    Prev
    Next
    INDEX
    Explanations

    words related to conventions, festivals and celebrations

    oai_token-act-pair · gemini-2.0-flash

    conferences, fairs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    chyma
    -0.51
    TagHelper
    -0.48
    риди
    -0.45
    ielo
    -0.45
    enziale
    -0.43
    olingo
    -0.43
     Są
    -0.41
    lohn
    -0.41
    semp
    -0.40
    pruch
    -0.40
    POSITIVE LOGITS
    <bos>
    1.13
     festival
    0.85
     Festival
    0.81
    Festival
    0.80
     FESTIVAL
    0.79
    Events
    0.77
     events
    0.76
     Festivals
    0.75
    WebControls
    0.75
    festival
    0.74
    Activations Density 0.659%

    No Known Activations