© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 57300
    Prev
    Next
    INDEX
    Explanations

    alone

    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_59_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
     ये
    1.11
    च
    0.68
    ये
    0.68
    こ
    0.65
    には
    0.63
    CH
    0.57
     یہ
    0.55
     यह
    0.52
     CH
    0.51
     या
    0.51
    POSITIVE LOGITS
     ही
    1.22
     alone
    1.10
     જ
    1.08
     ہی
    0.96
     Alone
    0.94
     saja
    0.89
    alone
    0.86
     ਹੀ
    0.84
    Alone
    0.78
     allein
    0.77
    Activations Density 0.003%

    No Known Activations