© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 2366
    Prev
    Next
    INDEX
    Explanations

    words related to formal events and celebrations, particularly those involving awards or recognition.

    oai_token-act-pair · gemini-2.0-flash

    celebratory events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    ittà
    -0.57
     FetchType
    -0.50
    сылкі
    -0.48
    Lähteet
    -0.47
     sacro
    -0.46
    estroyer
    -0.45
     numérique
    -0.45
    <?
    -0.45
     مصدر
    -0.45
    mergeFrom
    -0.45
    POSITIVE LOGITS
     banquet
    1.24
     party
    1.16
     Banquet
    1.00
    party
    0.97
     PARTY
    0.94
     Party
    0.93
     event
    0.87
    Party
    0.86
     dinner
    0.84
     annual
    0.84
    Activations Density 1.322%

    No Known Activations