© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 13437
    Prev
    Next
    INDEX
    Explanations

    the word "who"

    oai_token-act-pair · gemini-2.0-flash

    who

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
     who
    -3.58
    who
    -2.63
     whom
    -2.23
     którzy
    -2.02
     quien
    -1.98
    whom
    -1.93
     ktorí
    -1.91
     kteří
    -1.88
    Who
    -1.81
     whofe
    -1.78
    POSITIVE LOGITS
    :
    0.60
    j
    0.56
     =
    0.56
     -
    0.56
    en
    0.56
    /
    0.54
    9
    0.54
    _
    0.54
    :(
    0.52
    ,
    0.52
    Activations Density 1.259%

    No Known Activations