© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 201891
    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_46_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
     rentals
    0.42
    ቋ
    0.40
     available
    0.39
    ości
    0.38
     uniformed
    0.38
    感知
    0.38
     shirtless
    0.38
     disponíveis
    0.37
    perg
    0.37
    租赁
    0.37
    POSITIVE LOGITS
     詳細
    0.37
    শুর
    0.37
     pun
    0.36
     ব্রি
    0.36
    ushu
    0.35
     博文
    0.35
    끓
    0.35
    Boogie
    0.34
    ဇ
    0.34
     Merry
    0.33
    Activations Density 0.000%

    No Known Activations