© 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. 236841
    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
     কিল
    0.42
    MBOL
    0.40
     poor
    0.39
     lifespan
    0.38
    णिमा
    0.38
     pau
    0.37
     日
    0.37
    MnO
    0.37
     renewal
    0.37
     Cena
    0.37
    POSITIVE LOGITS
    руд
    0.37
    riva
    0.37
     डिजिट
    0.36
    пусти
    0.35
    liv
    0.34
     GES
    0.34
    吘
    0.33
     cPix
    0.32
    piperidin
    0.32
     tabBar
    0.32
    Activations Density 0.000%

    No Known Activations