© 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. 11683
    Prev
    Next
    INDEX
    Explanations

    the word "some" followed by another word

    oai_token-act-pair · gemini-2.0-flash

    words indicating groups or categorizations of people

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

    some

    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
     most
    -0.55
     many
    -0.55
    Kills
    -0.43
     moft
    -0.43
     çoğu
    -0.42
     muchos
    -0.42
    many
    -0.42
    antaine
    -0.41
    retung
    -0.41
     многие
    -0.41
    POSITIVE LOGITS
     theorists
    0.76
    rungsseite
    0.74
     experts
    0.72
     breeders
    0.72
    experts
    0.70
     designers
    0.70
     marketers
    0.69
     professionals
    0.67
     researchers
    0.67
     commentators
    0.67
    Activations Density 1.414%

    No Known Activations