© 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. 4873
    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
     we
    -0.66
     she
    -0.64
     so
    -0.63
    <bos>
    -0.57
     they
    -0.54
     you
    -0.53
     it
    -0.52
     y
    -0.52
     c
    -0.50
     w
    -0.49
    POSITIVE LOGITS
     pleaſure
    1.33
     Efq
    1.32
     myſelf
    1.31
     themſelves
    1.31
     himſelf
    1.30
     ſeveral
    1.29
     uſed
    1.29
     Monfieur
    1.28
     poffe
    1.25
     ſtate
    1.24
    Activations Density 0.307%

    No Known Activations