© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 162633
    Prev
    Next
    INDEX
    Explanations

    italian prefixes and 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_2_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
    ল
    1.60
    ל
    1.52
    ת
    1.52
    ل
    1.47
    ల
    1.38
    ल
    1.27
    ة
    1.23
    sch
    1.13
    د
    1.10
    л
    1.09
    POSITIVE LOGITS
     функция
    1.10
     δυνατό
    1.10
     فی
    1.08
     chiuso
    1.06
     второй
    1.05
     کل
    1.03
    ;
    1.03
     favoring
    1.02
     waging
    1.02
    .
    1.02
    Activations Density 0.000%

    No Known Activations