© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 3042
    Prev
    Next
    INDEX
    Explanations

    words related to United States elections, bills, and political processes.

    oai_token-act-pair · gemini-2.0-flash

    political events

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     myſelf
    -0.84
     Theſe
    -0.82
     Monfieur
    -0.82
     Efq
    -0.80
     Majefty
    -0.75
     Eſ
    -0.75
     itſelf
    -0.73
     feroit
    -0.73
     themſelves
    -0.72
    ſelf
    -0.71
    POSITIVE LOGITS
    帖最后由
    0.47
    usercontent
    0.47
    copyWith
    0.44
     Waray
    0.42
    Bronnen
    0.41
     mele
    0.38
     paga
    0.37
    udz
    0.36
     أجل
    0.36
    UnknownFieldSet
    0.36
    Activations Density 3.662%

    No Known Activations