© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 46
    Prev
    Next
    INDEX
    Explanations

    sentiments related to celebration, community, emotions and shared activities.

    oai_token-act-pair · gemini-2.0-flash

    Celebrate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    celebr
    -0.50
     celebration
    -0.50
     celebró
    -0.49
     celebrar
    -0.48
     CELEBR
    -0.47
     celebratory
    -0.44
     Celebration
    -0.44
     celebración
    -0.43
     celebrating
    -0.43
     celebrates
    -0.42
    POSITIVE LOGITS
    ValueStyle
    1.02
    AddTagHelper
    0.99
    UnusedPrivate
    0.96
    windowFixed
    0.92
    脚注の使い方
    0.85
    berdayakan
    0.83
    новниш
    0.83
    Билгалдахарш
    0.82
    providedIn
    0.81
     doInBackground
    0.81
    Activations Density 9.347%

    No Known Activations