© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 7600
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to events, especially tournaments, ceremonies, meetings, and parties.

    oai_token-act-pair · gemini-2.0-flash

    events being held or played

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    QApplication
    -0.58
    ToScroll
    -0.57
    printStackTrace
    -0.55
     переписи
    -0.54
     ut
    -0.52
    δρ
    -0.52
    ographed
    -0.51
    TagMode
    -0.48
    ǒ
    -0.47
    BAN
    -0.47
    POSITIVE LOGITS
    oredCriteria
    0.80
    elemField
    0.71
    GIVEREF
    0.65
    WriteTagHelper
    0.62
    ashian
    0.57
    Referanser
    0.57
     mergeFrom
    0.57
     defaultstate
    0.55
    SharedCtor
    0.52
    Rptr
    0.51
    Activations Density 3.704%

    No Known Activations