© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 14019
    Prev
    Next
    INDEX
    Explanations

    uses of the relative pronouns "who", "that", or "which", or the pronouns "they", "you", "person", "we", "somebody", or "everybody"

    oai_token-act-pair · gemini-2.0-flash

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     who
    -0.84
    who
    -0.82
     whom
    -0.70
     którzy
    -0.68
     kteří
    -0.66
    whom
    -0.63
    Who
    -0.62
    quién
    -0.58
     Who
    -0.56
     akik
    -0.55
    POSITIVE LOGITS
    цездатний
    0.73
    matchCondition
    0.73
    脚注の使い方
    0.71
     defaultstate
    0.69
     were
    0.69
     came
    0.68
    elfth
    0.68
    ⓧ
    0.67
     are
    0.65
    -------------</
    0.65
    Activations Density 2.305%

    No Known Activations