© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 13211
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to politics, specifically nominations, political positions, and politicians

    oai_token-act-pair · gemini-2.0-flash

    nominations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ApiModelProperty
    -0.49
    ingga
    -0.48
    )=>{
    -0.45
    grand
    -0.45
    teaching
    -0.44
     Riding
    -0.44
    entrepreneur
    -0.44
    artiges
    -0.44
     Routed
    -0.43
     mengajar
    -0.43
    POSITIVE LOGITS
    <bos>
    1.36
    Geplaatst
    0.80
     cherchés
    0.75
     itſelf
    0.72
    tagHelperRunner
    0.72
    IUrlHelper
    0.71
     متعلقه
    0.66
     незавершена
    0.65
    Personendaten
    0.62
    WriteTagHelper
    0.61
    Activations Density 2.573%

    No Known Activations