© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 198269
    Prev
    Next
    INDEX
    Explanations

    geographical places

    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_50_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
     اله
    0.55
     бер
    0.39
     EY
    0.38
     mistura
    0.37
     அதற்கு
    0.37
    ಯ್ಯ
    0.37
     H
    0.36
     подходя
    0.36
     Bharti
    0.36
     शिप
    0.36
    POSITIVE LOGITS
     J
    0.45
     mar
    0.41
    J
    0.41
     Niss
    0.40
     Winn
    0.39
     Sol
    0.37
    isance
    0.37
    Mard
    0.37
     cha
    0.37
     Marcel
    0.36
    Activations Density 0.000%

    No Known Activations