© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 62784
    Prev
    Next
    INDEX
    Explanations

    department after "why" or "which"

    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_11_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
     d
    0.68
     combustible
    0.64
     énorm
    0.61
     lounging
    0.60
     chauffage
    0.58
     rashes
    0.58
     avantage
    0.56
     foggy
    0.55
    रिडोर
    0.55
     перио
    0.54
    POSITIVE LOGITS
    et
    0.72
    ت
    0.72
    Ut
    0.71
    ת
    0.67
    Obs
    0.66
    Dlg
    0.65
    em
    0.64
    U
    0.64
    Tem
    0.63
    Otp
    0.61
    Activations Density 0.001%

    No Known Activations