© 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. 13929
    Prev
    Next
    INDEX
    Explanations

    instances of the word "power" in a political or technical context

    oai_token-act-pair · gemini-2.0-flash

    power

    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
    rungsseite
    -0.73
     following
    -0.69
     regular
    -0.68
     فريبيس
    -0.66
     kasarigan
    -0.65
     Chwiliwch
    -0.64
     one
    -0.63
     off
    -0.62
     the
    -0.62
    tanleria
    -0.62
    POSITIVE LOGITS
     Pliocene
    0.73
    NgModule
    0.69
     discogs
    0.69
     Hyperion
    0.69
     inanimate
    0.68
     recrystal
    0.68
    ContentAsync
    0.66
     harem
    0.66
     Poincaré
    0.66
     immortality
    0.65
    Activations Density 4.554%

    No Known Activations