© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 15252
    Prev
    Next
    INDEX
    Explanations

    political and governmental subjects, especially related to elections, parties, and leaders.

    oai_token-act-pair · gemini-2.0-flash

    variations of the word 'party'

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    -0.58
    Political
    -0.54
     politische
    -0.53
     política
    -0.52
     Politics
    -0.50
    دانشنامهٔ
    -0.50
     politically
    -0.49
     Poli
    -0.49
     politiques
    -0.48
    POLIT
    -0.48
    POSITIVE LOGITS
     party
    1.45
    party
    1.20
     parties
    1.20
     Party
    1.14
    parties
    1.13
     PARTY
    1.11
    Party
    1.11
    Personendaten
    1.07
    PARTY
    1.05
    Parties
    1.04
    Activations Density 2.381%

    No Known Activations