© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 218428
    Prev
    Next
    INDEX
    Explanations

    from followed by a noun or adjective

    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_31_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
    瑄
    0.47
     Evam
    0.42
     contr
    0.41
     promoc
    0.39
     ngan
    0.38
     analisis
    0.38
     keterangan
    0.38
     annotation
    0.37
     เช
    0.37
     Offers
    0.37
    POSITIVE LOGITS
    莉
    0.39
     fiercely
    0.39
    ลิ
    0.38
    UNESCO
    0.37
     ነው።
    0.36
     মুখ্যমন্ত্রী
    0.36
    <unused985>
    0.36
    CAA
    0.35
    itiers
    0.35
    നീ
    0.35
    Activations Density 0.004%

    No Known Activations