© 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. 11531
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to church events, addresses, and relationships

    oai_token-act-pair · gemini-2.0-flash

    Organizations

    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
     świata
    -0.54
     continuant
    -0.53
     έκ
    -0.52
     controlling
    -0.51
     světa
    -0.51
     kasarigan
    -0.50
     continúas
    -0.49
     unknownFields
    -0.48
     undivided
    -0.47
     ziren
    -0.47
    POSITIVE LOGITS
    ToListAsync
    0.51
     actionMode
    0.50
     Times
    0.48
     UnityEngine
    0.47
     Tabs
    0.47
    Примечания
    0.46
     Tab
    0.46
     Lips
    0.44
     corn
    0.44
     CORN
    0.44
    Activations Density 1.336%

    No Known Activations