© 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. 4888
    Prev
    Next
    INDEX
    Explanations

    the word "being" in various contexts

    oai_token-act-pair · gemini-2.0-flash

    phrases that involve the word "being"

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

    being

    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
     Theſe
    -0.68
     /\.
    -0.63
     Efq
    -0.63
     Beſ
    -0.59
    slidesPer
    -0.57
     whereof
    -0.57
    RectangleBorder
    -0.56
     Monfieur
    -0.55
     vectoriales
    -0.55
     NSCoder
    -0.55
    POSITIVE LOGITS
     đã
    0.65
     telah
    0.60
    vete
    0.56
     have
    0.56
     has
    0.56
    Autoritní
    0.55
     lived
    0.54
     run
    0.53
    եղ
    0.53
     ha
    0.52
    Activations Density 2.372%

    No Known Activations