© 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. 10451
    Prev
    Next
    INDEX
    Explanations

    the word "could" and related permissive words

    oai_token-act-pair · gemini-2.0-flash

    could

    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
     could
    -2.50
    could
    -2.00
     Could
    -1.74
    Could
    -1.73
     COULD
    -1.44
     myſelf
    -1.27
     podría
    -1.25
     itſelf
    -1.23
     könnte
    -1.23
     poderia
    -1.21
    POSITIVE LOGITS
     k
    0.77
    contentLoaded
    0.74
    kan
    0.65
    bes
    0.63
     z
    0.62
    ka
    0.60
    mok
    0.60
     du
    0.58
     hObject
    0.58
     d
    0.57
    Activations Density 0.562%

    No Known Activations