© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 260124
    Prev
    Next
    INDEX
    Explanations

    profanity ending in ck or tch

    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_22_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
    mann
    0.48
     बाब
    0.41
     elementary
    0.39
    ג
    0.38
    essero
    0.38
    Mo
    0.36
    rement
    0.36
    DY
    0.36
    lingen
    0.35
    gaan
    0.35
    POSITIVE LOGITS
    }')
    0.42
     testigos
    0.41
    وڑ
    0.39
    的使用
    0.38
     problemler
    0.37
     pTM
    0.37
     uninstall
    0.36
     decenas
    0.36
     пробле
    0.36
     شهد
    0.36
    Activations Density 0.002%

    No Known Activations