© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 8577
    Prev
    Next
    INDEX
    Explanations

    robe

    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_13_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
    к
    0.54
    _
    0.51
     swung
    0.50
    aktadır
    0.50
     к
    0.50
     annihilated
    0.50
     viết
    0.50
     rested
    0.50
     ejected
    0.49
     einfach
    0.49
    POSITIVE LOGITS
    maximizing
    0.55
    physiological
    0.48
    ULE
    0.48
    ORGAN
    0.47
    ਨ
    0.46
    춰
    0.46
     maximization
    0.46
    ባል
    0.46
    ண்டை
    0.45
    Normalized
    0.44
    Activations Density 0.000%

    No Known Activations