© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200252
    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_50_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
     rather
    0.43
     dislocations
    0.43
     quite
    0.41
    ຕ
    0.39
    TP
    0.39
    קט
    0.37
    Rm
    0.37
    --
    0.36
     $\
    0.36
    rather
    0.36
    POSITIVE LOGITS
     मैं
    0.63
     tôi
    0.63
     मैने
    0.60
    我不
    0.60
     Tôi
    0.59
     minha
    0.57
     আমি
    0.56
     mijn
    0.56
     હું
    0.56
     আমার
    0.55
    Activations Density 0.000%

    No Known Activations