© 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. 47216
    Prev
    Next
    INDEX
    Explanations

    predicting the future or its uncertainties

    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
     예측
    0.62
    ጪ
    0.57
     forecasts
    0.55
     прогноз
    0.55
     制
    0.54
    ensure
    0.54
     conlle
    0.53
     futuros
    0.53
    未来
    0.51
    预计
    0.51
    POSITIVE LOGITS
    ]
    0.73
    }
    0.55
     vacu
    0.52
    )
    0.51
     jedno
    0.49
    ísim
    0.49
     Pentium
    0.49
     Torrent
    0.48
    pedido
    0.47
     Mustangs
    0.46
    Activations Density 0.041%

    No Known Activations