© 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. 12414
    Prev
    Next
    INDEX
    Explanations

    the word "were"

    oai_token-act-pair · gemini-2.0-flash

    were

    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
     were
    -3.13
    Were
    -2.75
    were
    -2.53
     Were
    -2.48
     WERE
    -2.39
     Efq
    -2.11
     Theſe
    -2.00
     myſelf
    -1.98
     Monfieur
    -1.92
     furent
    -1.89
    POSITIVE LOGITS
     
    1.18
    ↵
    1.06
    <eos>
    1.03
    ↵↵
    1.01
    ,
    1.00
     a
    0.98
     (
    0.96
     is
    0.92
    .
    0.92
     in
    0.91
    Activations Density 2.101%

    No Known Activations