© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4694
    Prev
    Next
    INDEX
    Explanations

    the election process and associated ideas, especially presidential elections and candidates

    oai_token-act-pair · gemini-2.0-flash

    say "election"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     newBuilder
    -0.71
    SaveChangesAsync
    -0.67
    AFFIRMED
    -0.65
    ChildScrollView
    -0.61
    serviceWorker
    -0.58
    angé
    -0.57
    Obrázky
    -0.57
    urlpatterns
    -0.57
    isDebugEnabled
    -0.56
    Hochspringen
    -0.56
    POSITIVE LOGITS
     Ersten
    0.52
    kháu
    0.52
     BitSet
    0.51
     EGL
    0.50
    simp
    0.49
    ніципалі
    0.47
     refer
    0.45
     getList
    0.45
    elemField
    0.45
     sack
    0.45
    Activations Density 1.686%

    No Known Activations