© 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. 200775
    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
     tiến
    0.43
    aisa
    0.41
     Persever
    0.38
    ionar
    0.38
     دل
    0.38
     ස්
    0.38
     길
    0.37
     Contacts
    0.37
     মিড
    0.36
     मिड
    0.36
    POSITIVE LOGITS
    科學
    0.43
    科学
    0.40
     still
    0.40
    WW
    0.39
    डु
    0.39
    Still
    0.38
     popcorn
    0.38
    ++
    0.37
    bibli
    0.37
     scientific
    0.37
    Activations Density 0.000%

    No Known Activations