© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 27352
    Prev
    Next
    INDEX
    Explanations

    punish, punishment, punishing

    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_10_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
    u
    1.32
    j
    1.13
    ik
    1.08
    i
    1.06
    W
    1.05
    ä
    1.05
    a
    1.02
    M
    1.00
    ut
    1.00
    ra
    0.94
    POSITIVE LOGITS
     punish
    1.05
    罚
    0.95
     punishment
    0.84
     punished
    0.84
    惩
    0.82
     congratulate
    0.82
     penal
    0.81
    بی
    0.80
     exceedingly
    0.80
     phạt
    0.79
    Activations Density 0.019%

    No Known Activations