© 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-3-4B-IT
    3. 2-GEMMASCOPE-2-TRANSCODER-16K
    4. 324
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/transcoder_all/layer_2_width_16k_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
     faptul
    1.00
    ्स
    0.98
    ంచెం
    0.96
     noxious
    0.91
    टेगरी
    0.90
     cheques
    0.89
    ྐ
    0.89
    ẖ
    0.89
    $("#
    0.88
    थमिक
    0.87
    POSITIVE LOGITS
    ن
    1.59
    ので
    1.22
    an
    1.16
    お願い
    1.10
    Доб
    1.07
    특별시
    0.98
    ेक्षित
    0.97
    ح
    0.96
    美好
    0.96
    en
    0.92
    Activations Density 0.268%

    No Known Activations