© 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. 14574
    Prev
    Next
    INDEX
    Explanations

    the possessive adjective "your."

    oai_token-act-pair · gemini-2.0-flash

    your

    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
     your
    -3.64
    your
    -3.06
     yourself
    -2.42
     yourselves
    -2.36
     yours
    -2.23
    Your
    -2.19
     itſelf
    -2.19
     myſelf
    -2.11
     Monfieur
    -2.09
    YOUR
    -2.08
    POSITIVE LOGITS
     
    1.10
     (
    1.08
    ,
    1.04
    <eos>
    1.03
     “
    1.01
     "
    0.98
    ↵
    0.94
      
    0.90
    .
    0.88
    ...
    0.87
    Activations Density 1.023%

    No Known Activations