© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8386
    Prev
    Next
    INDEX
    Explanations

    words ending in "s" or which may otherwise be plural nouns

    oai_token-act-pair · gemini-2.0-flash

    plural nouns Method used: 1. Reason: identical plural form across tokens

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     kayaks
    -1.59
     canoes
    -1.41
     shovels
    -1.39
     napkins
    -1.38
     wreaths
    -1.37
     aprons
    -1.34
     bikinis
    -1.30
     bagels
    -1.30
     chopsticks
    -1.30
     handker
    -1.30
    POSITIVE LOGITS
     top
    0.69
     large
    0.66
    ors
    0.66
    ons
    0.65
     pas
    0.65
     series
    0.65
     jag
    0.64
    ures
    0.60
     push
    0.60
     nos
    0.59
    Activations Density 5.841%

    No Known Activations