© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42788
    Prev
    Next
    INDEX
    Explanations

    shots and runs

    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_22_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kesehatan
    0.34
    আপ
    0.33
     healthier
    0.33
     ਦਵਾਈ
    0.32
     médicament
    0.31
    櫃
    0.31
     `>`,
    0.31
     sveik
    0.31
     lasting
    0.31
    asiswa
    0.31
    POSITIVE LOGITS
     c
    0.33
    ʎ
    0.32
    c
    0.32
    radas
    0.29
    ndi
    0.29
     muš
    0.29
     Ә
    0.29
    ారులు
    0.28
     dwóch
    0.28
    ynı
    0.27
    Activations Density 0.001%

    No Known Activations