© 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. 3628
    Prev
    Next
    INDEX
    Explanations

    the word "you"

    oai_token-act-pair · gemini-2.0-flash

    you

    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
    -0.95
     I
    -0.91
     we
    -0.91
     you
    -0.83
     can
    -0.78
     You
    -0.72
     be
    -0.70
     he
    -0.69
    ,
    -0.68
     it
    -0.66
    POSITIVE LOGITS
     kasarigan
    0.88
    them
    0.85
     itſelf
    0.83
    UserScript
    0.81
    Diweddarwch
    0.81
     Reſ
    0.80
     greateſt
    0.78
     pleaſure
    0.78
     Diſ
    0.78
     שוליים
    0.77
    Activations Density 0.368%

    No Known Activations