© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 203860
    Prev
    Next
    INDEX
    Explanations

    Japanese verbs

    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
    Negative Logits
    で行
    0.43
    的气
    0.42
     Rows
    0.41
     !!,
    0.41
    气
    0.40
     !\
    0.39
    ：「
    0.39
     !}\
    0.38
     ¿?
    0.37
    ような
    0.37
    POSITIVE LOGITS
     삽니다
    0.46
    います
    0.45
    thus
    0.43
    となります
    0.43
    めます
    0.42
     fa
    0.40
    られます
    0.40
    かります
    0.40
    みます
    0.39
     thus
    0.39
    Activations Density 0.000%

    No Known Activations