© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 164951
    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_31_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
     إذ
    0.38
    mathcal
    0.37
     wheel
    0.36
     пресс
    0.36
     രോഗ
    0.35
     (€
    0.35
     aneu
    0.35
     ansi
    0.35
    牒
    0.35
     ホイール
    0.35
    POSITIVE LOGITS
     appearances
    0.39
     යු
    0.39
     permissible
    0.38
     salons
    0.37
     subspaces
    0.37
     permis
    0.36
     slavery
    0.36
     pleasurable
    0.35
     mercy
    0.35
     sited
    0.35
    Activations Density 0.000%

    No Known Activations