© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 37100
    Prev
    Next
    INDEX
    Explanations

    neko sounds

    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_50_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
     Glut
    0.45
     War
    0.45
     Bim
    0.45
    わり
    0.44
    War
    0.43
     wa
    0.42
    wari
    0.42
     Wa
    0.41
    華
    0.41
     bim
    0.40
    POSITIVE LOGITS
    ね
    1.27
     ne
    1.25
     nek
    1.16
     Nek
    1.14
    ネ
    1.12
     NE
    1.11
     네
    1.10
     né
    1.09
    네
    1.08
     Ne
    1.03
    Activations Density 0.051%

    No Known Activations