© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 14470
    Prev
    Next
    INDEX
    Explanations

    words associated with American politics and law.

    oai_token-act-pair · gemini-2.0-flash

    party

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     Political
    -1.00
     politically
    -0.98
    Political
    -0.92
     POLITICAL
    -0.86
     political
    -0.86
    political
    -0.81
     Poli
    -0.80
    Poli
    -0.79
    poli
    -0.78
     politischen
    -0.77
    POSITIVE LOGITS
     party
    1.48
    party
    1.26
     Party
    1.14
     PARTY
    1.13
    Party
    1.13
    PARTY
    1.02
     partij
    0.81
     autorytatywna
    0.65
     Partei
    0.64
     Parties
    0.58
    Activations Density 7.533%

    No Known Activations