© 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
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5232
    Prev
    Next
    INDEX
    Explanations

    phrases indicating difficulty, setbacks or problems

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'pain'

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

    pain

    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
    cyjne
    -0.63
    cyjny
    -0.61
     rechange
    -0.49
     betweenstory
    -0.48
    ềm
    -0.47
    jalá
    -0.45
    المصدر
    -0.44
    spyOn
    -0.43
    éraire
    -0.43
     بيها
    -0.43
    POSITIVE LOGITS
     pain
    1.01
    Pain
    0.85
     PAIN
    0.83
     Pain
    0.77
    pain
    0.75
    וויק
    0.65
     pains
    0.63
     Schmerz
    0.63
     @"/
    0.60
     douleur
    0.58
    Activations Density 0.421%

    No Known Activations