© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 6-GEMMASCOPE-2-TRANSCODER-262K
    7. 205665
    Prev
    Next
    INDEX
    Explanations

    "sexting" after AI assistant limitations

    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_6_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
     İstifadə
    1.05
    𝚕
    1.02
     Перейти
    1.00
     Εκ
    1.00
    lç
    0.99
    も含
    0.98
     ৃ
    0.98
    lt
    0.97
     provoqu
    0.97
    larını
    0.95
    POSITIVE LOGITS
    س
    1.38
    in
    1.25
    ار
    1.16
    지
    1.07
    را
    1.01
    دا
    0.98
    (
    0.98
    บ
    0.98
    ad
    0.97
    ட
    0.96
    Activations Density 0.000%

    No Known Activations