© 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. 113432
    Prev
    Next
    INDEX
    Explanations

    German word endings like 'cht'

    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
    cano
    1.02
    ként
    1.01
    cC
    0.97
    f
    0.97
    cale
    0.95
    cH
    0.95
    cient
    0.94
    h
    0.94
    cir
    0.92
    ﺮ
    0.92
    POSITIVE LOGITS
    ي
    1.87
    ع
    1.36
    ר
    1.27
    um
    1.14
    ين
    1.13
    ر
    1.08
     de
    1.05
    اك
    1.04
    ak
    1.03
    ت
    1.03
    Activations Density 0.000%

    No Known Activations