© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5370
    Prev
    Next
    INDEX
    Explanations

    words related to the act of voting, voter turnout, and elections

    oai_token-act-pair · gemini-2.0-flash

    vote

    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
     the
    -1.21
      
    -1.05
     a
    -1.02
     
    -0.96
     in
    -0.94
     an
    -0.90
     all
    -0.90
    ,
    -0.90
     “
    -0.81
     just
    -0.81
    POSITIVE LOGITS
     ainfi
    1.41
     plufieurs
    1.40
     avoient
    1.31
     auroit
    1.26
     engraçadas
    1.26
     feroit
    1.25
     titolata
    1.25
     étoit
    1.23
     Efq
    1.23
    OGND
    1.23
    Activations Density 1.907%

    No Known Activations