© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 4388
    Prev
    Next
    INDEX
    Explanations

    words related to historical politics and government

    oai_token-act-pair · gemini-2.0-flash

    politics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Monfieur
    -1.26
     Theſe
    -1.16
     Jefus
    -1.15
     Reſ
    -1.13
     Efq
    -1.13
     Diſ
    -1.08
     ſever
    -1.08
     themſelves
    -1.08
     himſelf
    -1.07
     Anſ
    -1.05
    POSITIVE LOGITS
    viper
    0.36
    chtet
    0.34
     ex
    0.33
     defaultstate
    0.32
    wns
    0.31
     ‘
    0.31
     coar
    0.30
    Տես
    0.30
     logística
    0.29
     
    0.29
    Activations Density 26.043%

    No Known Activations