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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218152
    Prev
    Next
    INDEX
    Explanations

    asserting independence or autonomy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ností
    0.43
    ências
    0.40
     Ки
    0.38
     taps
    0.37
     Πα
    0.37
    పె
    0.37
    тріш
    0.37
    釋
    0.36
    益
    0.36
     সেপ্ট
    0.36
    POSITIVE LOGITS
     stubborn
    0.70
     autonomy
    0.46
     जिद
    0.45
     stubbornly
    0.44
     autonom
    0.43
     autonomous
    0.43
    autonomous
    0.43
     inflexible
    0.41
     rebellious
    0.41
    犟
    0.41
    Activations Density 0.003%

    No Known Activations