© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 94068
    Prev
    Next
    INDEX
    Explanations

    learning and tasks

    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_60_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
    may
    0.68
     may
    0.50
    為
    0.45
     కే
    0.42
     May
    0.41
     為
    0.41
    amay
    0.40
    为
    0.40
     为
    0.39
    May
    0.38
    POSITIVE LOGITS
     likely
    1.08
    likely
    0.74
     more
    0.70
    没有
    0.69
    沒有
    0.66
    是没有
    0.66
     Likely
    0.64
    更多
    0.63
     mehr
    0.61
    更多的
    0.58
    Activations Density 0.002%

    No Known Activations