© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 30919
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     Lehr
    0.46
     पुरालेखित
    0.41
    ameva
    0.39
     ActivityCompat
    0.38
    )})$
    0.38
    يلا
    0.37
    uillez
    0.37
    impress
    0.37
    چان
    0.36
    érence
    0.36
    POSITIVE LOGITS
    allus
    0.43
     Roux
    0.42
    Warehouse
    0.39
    驹
    0.39
    all
    0.38
     voice
    0.38
     paral
    0.37
     Paral
    0.37
     пет
    0.37
     развитии
    0.36
    Activations Density 0.000%

    No Known Activations