© 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. 48536
    Prev
    Next
    INDEX
    Explanations

    hilarious or sarcastic humor

    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
    ست
    0.36
    v
    0.32
    न
    0.32
    Z
    0.32
    ):
    0.30
     htmlFor
    0.29
    ாரா
    0.29
     topRight
    0.29
    Q
    0.29
    AY
    0.29
    POSITIVE LOGITS
    daki
    0.38
    of
    0.38
    istles
    0.37
      
    0.34
     It
    0.33
    㗆
    0.33
     сервис
    0.32
     cidades
    0.32
    deling
    0.31
     तुम्ही
    0.31
    Activations Density 0.042%

    No Known Activations