© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 7383
    Prev
    Next
    INDEX
    Explanations

    the word "couple," and sometimes "weds".

    oai_token-act-pair · gemini-2.0-flash

    couple

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     couple
    -2.84
    couple
    -2.61
     Couple
    -2.42
    Couple
    -2.41
     couples
    -2.09
    couples
    -1.81
     Couples
    -1.80
     casal
    -1.55
     COU
    -1.39
     pair
    -1.36
    POSITIVE LOGITS
    הערות
    0.49
     együtt
    0.46
     lepší
    0.45
     arasında
    0.43
     eingestellt
    0.41
    hø
    0.39
     kell
    0.39
     samband
    0.38
    ambo
    0.37
     bré
    0.37
    Activations Density 0.453%

    No Known Activations