© 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
    2. Gemma-3-27B-IT
    3. 22-GEMMASCOPE-2-TRANSCODER-262K
    4. 260489
    Prev
    Next
    INDEX
    Explanations

    client-patient information privacy

    np_acts-logits-general · gemini-2.5-flash-lite

    legal profession and its ethical obligations.

    oai_token-act-pair · gemini-2.5-flash-liteTriggered by @enricobottazzi

    confidential information

    np_max-act-logits · gemini-2.5-flash-liteTriggered by @enricobottazzi
    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
    esistenza
    0.43
     existência
    0.39
    Existence
    0.38
    UNIQUE
    0.38
     existence
    0.38
    存在
    0.38
    되고
    0.37
     mang
    0.36
     sudd
    0.36
     وان
    0.36
    POSITIVE LOGITS
     McK
    0.45
     McC
    0.41
     Cutter
    0.41
     Orleans
    0.40
     Bella
    0.40
     Physics
    0.40
    खरी
    0.40
     Austin
    0.40
    ork
    0.39
     Hebrew
    0.39
    Activations Density 0.004%

    No Known Activations