© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141854
    Prev
    Next
    INDEX
    Explanations

    structure

    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
    ნიშვნ
    0.40
    ektion
    0.34
    وقف
    0.33
    ượ
    0.33
     swallow
    0.33
    oruč
    0.32
     выполнение
    0.32
    ễ
    0.32
    തിരെ
    0.31
     ремонт
    0.31
    POSITIVE LOGITS
     structured
    2.08
     structure
    1.96
     струк
    1.89
    structured
    1.88
     Structured
    1.88
    结构
    1.87
    Structured
    1.86
     STRUCTURE
    1.83
     Structure
    1.82
     estruct
    1.81
    Activations Density 0.283%

    No Known Activations