© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 248499
    Prev
    Next
    INDEX
    Explanations

    say "De"

    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_56_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
    ාවිත
    0.41
     dissolving
    0.36
    რთ
    0.35
     uphol
    0.34
    ிருக்கு
    0.34
    峨
    0.34
    님
    0.34
     दशक
    0.33
    delim
    0.33
    ceq
    0.33
    POSITIVE LOGITS
     De
    3.00
    De
    2.77
    de
    2.33
     де
    1.82
    德
    1.82
     दे
    1.81
    <0xA4>
    1.77
     DE
    1.76
     ده
    1.59
    デ
    1.58
    Activations Density 0.003%

    No Known Activations