© 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
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37954
    Prev
    Next
    INDEX
    Explanations

    municipal mayor borough

    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_11_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
     hydrolysis
    0.54
    TF
    0.52
     हिसाब
    0.51
    داد
    0.50
    ╽
    0.50
     dividido
    0.48
    ﻄ
    0.48
    ﺭ
    0.48
    ﻒ
    0.48
    ﻤ
    0.47
    POSITIVE LOGITS
     Букмекерлар
    0.54
    wohn
    0.53
    ید
    0.50
     เหมือน
    0.50
    ovir
    0.49
     সীমান্তবর্তী
    0.49
    ocin
    0.49
    StateException
    0.49
     शेतक
    0.49
    eci
    0.49
    Activations Density 0.000%

    No Known Activations