© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16162
    Prev
    Next
    INDEX
    Explanations

    time periods and locations

    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_40_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
     curd
    0.39
    áneas
    0.39
    Dictionaries
    0.38
     مر
    0.37
     auront
    0.37
     dicembre
    0.37
    权重
    0.36
     TP
    0.36
    --)
    0.36
     पिस्टल
    0.36
    POSITIVE LOGITS
    Erik
    0.41
     regular
    0.40
    regular
    0.38
    eken
    0.38
     String
    0.37
     Regular
    0.37
    acaktır
    0.37
     Erik
    0.37
    special
    0.36
     예술
    0.36
    Activations Density 0.009%

    No Known Activations