© 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. 77745
    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
    📥
    0.37
     టై
    0.37
    GET
    0.37
     肌
    0.37
     جار
    0.35
    ᠨ
    0.34
     ይሰ
    0.34
    该
    0.34
    ルダー
    0.34
    Murray
    0.34
    POSITIVE LOGITS
    adhi
    0.47
    ၡ
    0.45
    loo
    0.43
     Supervisory
    0.39
    ukar
    0.39
    trade
    0.38
    umpy
    0.38
    hus
    0.37
     trade
    0.37
     funktioniert
    0.37
    Activations Density 0.000%

    No Known Activations