© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9816
    Prev
    Next
    INDEX
    Explanations

    the word "willing" and sometimes words associated with desire or interest

    oai_token-act-pair · gemini-2.0-flash

    willing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     willing
    -1.81
    willing
    -1.59
     willingness
    -1.27
     Willing
    -1.18
     Exacts
    -1.04
    Willing
    -1.02
     unwilling
    -0.97
    Personendaten
    -0.94
     незавершена
    -0.92
    adpleegd
    -0.91
    POSITIVE LOGITS
    </b>
    0.54
    生的
    0.50
    setPref
    0.49
     are
    0.48
     humaines
    0.44
    :
    0.44
     program
    0.43
     Fel
    0.42
    ul
    0.42
    IJ
    0.42
    Activations Density 1.047%

    No Known Activations