© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 47216
    Prev
    Next
    INDEX
    Explanations

    Vietnamese words and UI elements

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    t
    0.98
     I
    0.88
    d
    0.87
    ل
    0.74
    p
    0.71
    h
    0.70
    ků
    0.65
    dA
    0.64
     on
    0.63
    تى
    0.61
    POSITIVE LOGITS
    ва
    0.71
    ম্বা
    0.66
     fundador
    0.64
    ங்கள்
    0.63
    \%,
    0.62
    нией
    0.59
     pewno
    0.59
     algoritmo
    0.59
    ပိုင်း
    0.58
    任意の
    0.58
    Activations Density 0.033%

    No Known Activations