© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 247569
    Prev
    Next
    INDEX
    Explanations

    jumping and leaping

    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_40_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
     लोहा
    0.42
     disb
    0.41
     Transl
    0.40
     usos
    0.40
     دینا
    0.40
    馁
    0.39
    ശയ
    0.39
     kullanılır
    0.38
    惧
    0.38
     translating
    0.38
    POSITIVE LOGITS
     leapt
    0.48
    躍
    0.45
    跳
    0.44
     leap
    0.43
     jumping
    0.43
     jump
    0.42
     jumped
    0.41
     Jumping
    0.40
     leaped
    0.39
    jumping
    0.39
    Activations Density 0.000%

    No Known Activations