© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 158831
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ع
    2.00
    ت
    1.71
    י
    1.59
    ה
    1.49
    פ
    1.40
    מ
    1.39
    ي
    1.33
    ش
    1.23
    އ
    1.23
    的游戏
    1.22
    POSITIVE LOGITS
    ill
    1.21
     I
    1.18
     It
    1.15
    aj
    1.09
    ifrån
    1.09
    itt
    1.06
     it
    1.05
    ast
    1.05
     the
    1.04
    ä
    1.02
    Activations Density 0.000%

    No Known Activations