© 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. 12378
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to social gatherings or political actions in dedication to a person, place, cause, or idea.

    oai_token-act-pair · gemini-2.0-flash

    events and ceremonies

    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
    UnusedPrivate
    -0.60
    XmlType
    -0.57
    Rhestr
    -0.52
    catori
    -0.51
     Add
    -0.51
     TextAppearance
    -0.50
     producing
    -0.50
     JpaRepository
    -0.49
     flag
    -0.49
     الحره
    -0.49
    POSITIVE LOGITS
    expandindo
    0.86
    twimg
    0.56
    MemoryWarning
    0.54
    EPs
    0.53
     Light
    0.52
    وفي
    0.50
    EP
    0.50
    Light
    0.49
    drawSprites
    0.49
    Weblinks
    0.48
    Activations Density 7.992%

    No Known Activations