© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 3259
    Prev
    Next
    INDEX
    Explanations

    sexually suggestive

    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_39_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
    愛
    0.43
    ಿಸುತ್ತ
    0.41
     ভালবাস
    0.40
     adip
    0.38
     Love
    0.37
     사랑
    0.37
    Love
    0.37
    爱
    0.36
     Bedford
    0.36
     любовь
    0.35
    POSITIVE LOGITS
     EXCHANGE
    0.39
     sek
    0.39
     एक्सचेंज
    0.37
    ："
    0.37
    عاية
    0.37
    ርስዎ
    0.36
     exchanged
    0.36
     mục
    0.36
    sev
    0.35
     Weird
    0.35
    Activations Density 0.189%

    No Known Activations