© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 2924
    Prev
    Next
    INDEX
    Explanations

    instances of the word "decide".

    oai_token-act-pair · gemini-2.0-flash

    decide

    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
    Negative Logits
     propOrder
    -0.90
    homonymie
    -0.76
    simpleType
    -0.74
     as
    -0.73
     et
    -0.69
     disponibilités
    -0.68
     est
    -0.68
     ma
    -0.64
     her
    -0.62
     mit
    -0.62
    POSITIVE LOGITS
     itſelf
    1.39
     Shakspeare
    1.33
     faſt
    1.24
     myſelf
    1.24
     Monfieur
    1.20
     ſtand
    1.19
     themſelves
    1.18
     Theſe
    1.17
     uſe
    1.16
     Anſ
    1.14
    Activations Density 1.253%

    No Known Activations