© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 247984
    Prev
    Next
    INDEX
    Explanations

    bad harvests

    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_56_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
    作
    1.81
     cultures
    1.44
    작
    1.40
     작
    1.38
    cultures
    1.33
     Cultures
    1.28
     culturas
    1.28
     harvest
    1.24
     作
    1.18
    Culture
    1.16
    POSITIVE LOGITS
     pan
    0.93
     Pan
    0.71
    pan
    0.71
    Pan
    0.68
     PAN
    0.48
    PAN
    0.46
     पैन
    0.45
    accoon
    0.39
     pancreatitis
    0.39
    پان
    0.39
    Activations Density 0.001%

    No Known Activations