© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 200821
    Prev
    Next
    INDEX
    Explanations

    Cambridge Analytica manipulation scandal

    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_37_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
     dirig
    0.38
    ELIG
    0.38
    鑑
    0.38
    ISTA
    0.37
    רות
    0.37
     england
    0.36
    鵬
    0.36
     év
    0.36
    緊張
    0.35
    CommandHandler
    0.35
    POSITIVE LOGITS
    用户的
    0.50
     ἐν
    0.44
     کاربران
    0.43
    тому
    0.43
     manipulate
    0.42
    acil
    0.42
     সম্পাদকীয়
    0.41
     متابعي
    0.41
    ユーザー
    0.40
     пользователей
    0.40
    Activations Density 0.003%

    No Known Activations