© 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. 154467
    Prev
    Next
    INDEX
    Explanations

    A

    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
     அட்சய
    0.37
     Janice
    0.37
     Unde
    0.37
    ুস
    0.36
    Bub
    0.36
    ഒ
    0.36
    Arena
    0.36
    𝗢
    0.36
     dosages
    0.36
     slay
    0.36
    POSITIVE LOGITS
    ital
    0.46
    umerable
    0.42
     façons
    0.41
    راق
    0.40
     católica
    0.40
    țional
    0.40
    idable
    0.39
    ħ
    0.39
    arket
    0.38
    iril
    0.38
    Activations Density 0.000%

    No Known Activations