© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4464
    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_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     who
    -1.47
    who
    -1.40
    Who
    -1.34
     Who
    -1.22
     whom
    -1.16
    whom
    -1.02
    WHO
    -0.99
    <bos>
    -0.93
     WHO
    -0.91
     Whom
    -0.90
    POSITIVE LOGITS
     MainAxisSize
    0.82
    Portale
    0.68
    principalColumn
    0.65
    StoryboardSegue
    0.62
    WriteLiteral
    0.58
    posedge
    0.58
     ddelweddau
    0.57
     defStyle
    0.56
    󠁢
    0.56
    endphp
    0.55
    Activations Density 0.976%

    No Known Activations