© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 129233
    Prev
    Next
    INDEX
    Explanations

    Hungarian and English words ending in suffixes

    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_1_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
    0
    1.91
    자
    1.59
    ۰
    1.44
    ０
    1.41
    리
    1.34
    ده
    1.23
    수
    1.23
     at
    1.22
    ский
    1.20
    ہ
    1.20
    POSITIVE LOGITS
    c
    1.15
     I
    1.09
    I
    1.05
     Section
    0.95
    under
    0.89
    head
    0.88
    ണ
    0.86
    قية
    0.85
    ia
    0.82
     That
    0.82
    Activations Density 0.000%

    No Known Activations