© 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. 134170
    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝚁
    0.39
    বিধান
    0.39
    უნქ
    0.39
     لكم
    0.39
    шт
    0.38
    oncer
    0.37
    인트
    0.37
    痂
    0.37
    PLACEMENT
    0.36
    ාවිත
    0.36
    POSITIVE LOGITS
     Nav
    0.42
     …
    0.41
    Nav
    0.41
    ew
    0.40
     Reprodu
    0.39
     ACC
    0.39
    nav
    0.37
     Acc
    0.37
     Ingersoll
    0.36
     Yaw
    0.36
    Activations Density 0.000%

    No Known Activations