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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 196714
    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_27_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
     казіно
    0.43
    듕
    0.41
     ښ
    0.39
    מצא
    0.39
    经费
    0.37
     académ
    0.36
    üre
    0.36
    oglobine
    0.35
    weapp
    0.35
    ╡
    0.35
    POSITIVE LOGITS
     bay
    0.47
     Bayesian
    0.41
     sectors
    0.41
     bays
    0.39
     subdivided
    0.39
     routines
    0.38
     permutations
    0.38
     wrappers
    0.38
     decreasing
    0.37
     con
    0.37
    Activations Density 0.000%

    No Known Activations