© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 38939
    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_57_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
    公
    0.43
     Hyper
    0.40
     public
    0.40
     PUBLIC
    0.39
     Hyp
    0.38
     सार्वजनिक
    0.38
    ومن
    0.38
     traces
    0.37
    Hyper
    0.36
     Yellow
    0.36
    POSITIVE LOGITS
    seekg
    0.41
     foule
    0.38
    澀
    0.38
     curso
    0.38
     generality
    0.38
     اعت
    0.37
     fréquence
    0.36
     শব
    0.36
     autour
    0.36
    orthogonal
    0.36
    Activations Density 0.000%

    No Known Activations