© 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. 165001
    Prev
    Next
    INDEX
    Explanations

    criticizing or insulting

    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
     rejects
    0.39
     rejected
    0.37
     rejecting
    0.36
     reject
    0.35
     Bonjour
    0.34
     இல
    0.33
     swims
    0.33
    鑲
    0.33
     odd
    0.32
     jal
    0.32
    POSITIVE LOGITS
     defam
    0.37
    謗
    0.37
     अपमान
    0.37
    诽
    0.37
    ধ্বনি
    0.36
    ripty
    0.35
     utt
    0.35
     defamation
    0.34
    譏
    0.34
     ressent
    0.34
    Activations Density 0.002%

    No Known Activations