© 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. 3498
    Prev
    Next
    INDEX
    Explanations

    the pronoun "they" or its possessive form.

    oai_token-act-pair · gemini-2.0-flash

    they

    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
     they
    -4.03
    they
    -3.14
     они
    -2.69
    They
    -2.58
     вони
    -2.47
    彼らは
    -2.20
     mereka
    -2.19
     They
    -2.16
     THEY
    -2.11
    mereka
    -2.11
    POSITIVE LOGITS
     
    0.99
     She
    0.92
     us
    0.90
     (
    0.84
     a
    0.79
     him
    0.77
    .
    0.77
    ,
    0.77
     C
    0.77
     We
    0.76
    Activations Density 2.132%

    No Known Activations