© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10821
    Prev
    Next
    INDEX
    Explanations

    words relating to importance or significance

    oai_token-act-pair · gemini-2.0-flash

    technical, scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     important
    -1.82
    important
    -1.65
     crucial
    -1.58
     Important
    -1.48
     essential
    -1.45
     vital
    -1.43
    Important
    -1.38
     belangrijke
    -1.30
    重要
    -1.28
     key
    -1.27
    POSITIVE LOGITS
     numberOfRows
    0.50
    TintMode
    0.45
     Directly
    0.45
     přímo
    0.44
    TestingModule
    0.44
     diretamente
    0.44
    ाषा
    0.43
    JspWriter
    0.43
    sträger
    0.42
     directly
    0.42
    Activations Density 3.510%

    No Known Activations