© 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. 180076
    Prev
    Next
    INDEX
    Explanations

    W

    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
     常
    0.42
    emm
    0.40
     bounding
    0.40
    常
    0.39
    ins
    0.39
     Zab
    0.39
     rips
    0.39
     guardians
    0.38
     O
    0.38
     density
    0.38
    POSITIVE LOGITS
     دستاویز
    0.43
    Ro
    0.42
    ιβ
    0.41
     ThemeOverlay
    0.41
    аст
    0.39
    Athens
    0.39
    akath
    0.38
     foray
    0.38
    വാൻ
    0.38
    ovll
    0.38
    Activations Density 0.001%

    No Known Activations