© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 196999
    Prev
    Next
    INDEX
    Explanations

    postal codes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    的信息
    0.43
     المعلومات
    0.39
     сообщения
    0.39
     Информация
    0.38
    玲
    0.38
     Merk
    0.38
     Qxb
    0.37
     స్ట
    0.37
     информация
    0.37
     ultimatum
    0.36
    POSITIVE LOGITS
    தியை
    0.42
    histor
    0.39
    <0x93>
    0.39
    ध्य
    0.38
    ธิ
    0.37
     unfore
    0.37
    flow
    0.37
     Avoiding
    0.37
     Brion
    0.36
    पालिका
    0.36
    Activations Density 0.000%

    No Known Activations