© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 42574
    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_22_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
     शेफाली
    0.52
    ти
    0.48
    दी
    0.48
    참
    0.48
     annealed
    0.48
     посмотрим
    0.47
    átiles
    0.47
    र
    0.47
    ással
    0.46
    மக்கள்
    0.46
    POSITIVE LOGITS
     rights
    0.46
     fuer
    0.43
     calcul
    0.42
     صنع
    0.41
     連
    0.41
     ورح
    0.40
     constru
    0.40
    uild
    0.40
     তর
    0.39
    詮
    0.39
    Activations Density 0.000%

    No Known Activations