© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 11992
    Prev
    Next
    INDEX
    Explanations

    the pronouns "he", "she", "his", and "her"

    oai_token-act-pair · gemini-2.0-flash

    pronouns he and she

    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
    Not in Any Lists

    No Comments

    Negative Logits
     the
    -1.26
     another
    -1.01
     his
    -0.99
     both
    -0.98
     her
    -0.93
     then
    -0.93
     it
    -0.93
     she
    -0.91
     as
    -0.90
     again
    -0.89
    POSITIVE LOGITS
    <bos>
    1.54
    e
    0.82
    "
    0.78
    a
    0.74
    ن
    0.72
    i
    0.72
    ↵
    0.71
    A
    0.71
    '
    0.70
    o
    0.69
    Activations Density 0.605%

    No Known Activations