© 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
    2. Gemma-3-27B-IT
    3. 9-GEMMASCOPE-2-TRANSCODER-262K
    4. 196414
    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_9_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
    Ĝ
    0.52
     भट्ट
    0.51
     itd
    0.49
    ㌔
    0.49
     hypothalam
    0.47
     nostrum
    0.46
    ྷ
    0.46
     NG
    0.45
     puta
    0.45
     xc
    0.45
    POSITIVE LOGITS
    je
    0.55
     Ste
    0.46
     Fifty
    0.45
    нер
    0.43
    jum
    0.43
    জী
    0.42
    chev
    0.42
     categorías
    0.42
    jaer
    0.42
     Bark
    0.41
    Activations Density 0.000%

    No Known Activations