© 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-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228789
    Prev
    Next
    INDEX
    Explanations

    insults

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     insults
    1.28
     insulting
    1.23
     insult
    1.20
     mocking
    1.16
     insulted
    1.07
     mocks
    1.05
     mocked
    1.03
    嘲
    1.00
     bullying
    0.99
     ridicule
    0.95
    POSITIVE LOGITS
    omorphism
    0.42
    ngthen
    0.39
    უშა
    0.38
    collapse
    0.38
     기울
    0.37
    蓊
    0.37
    𝙳
    0.36
    idency
    0.35
     खरा
    0.35
     मिलाकर
    0.35
    Activations Density 0.122%

    No Known Activations