© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10820
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to professions, hobbies and entertainment

    oai_token-act-pair · gemini-2.0-flash

    terms related to manufacturing processes

    np_token-act-pair-logits · gpt-4o-mini

    industries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     digitais
    -0.62
     autorité
    -0.55
     espirituales
    -0.53
     vectoriales
    -0.51
     vuestros
    -0.49
     internas
    -0.49
    #![
    -0.49
     estratég
    -0.49
     cotone
    -0.48
    CloseOperation
    -0.47
    POSITIVE LOGITS
     aspect
    1.09
     process
    1.07
     part
    0.94
     sector
    0.94
     market
    0.88
     portion
    0.84
     scene
    0.83
     industry
    0.80
     element
    0.80
    process
    0.78
    Activations Density 3.563%

    No Known Activations