© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82613
    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_53_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
     ө
    0.65
     т
    0.56
     төр
    0.52
     м
    0.51
    Ө
    0.49
     тө
    0.48
     sostuvo
    0.48
    ө
    0.47
     Ө
    0.46
     meg
    0.45
    POSITIVE LOGITS
    ellan
    0.41
    uckle
    0.40
    لمين
    0.40
    UTILS
    0.38
    ulls
    0.38
     UIKit
    0.38
    lern
    0.38
    llam
    0.38
    荇
    0.37
    aments
    0.37
    Activations Density 0.000%

    No Known Activations