© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173300
    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_20_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
     Tory
    0.47
     ۳
    0.47
     mail
    0.46
     Hei
    0.46
     bas
    0.45
     Ku
    0.43
     Mail
    0.43
     Bas
    0.42
     mailing
    0.42
    \}$.
    0.42
    POSITIVE LOGITS
    神
    0.49
     분위
    0.46
    手
    0.46
    中国
    0.46
    apache
    0.45
     ఆది
    0.45
    重要
    0.44
    gluc
    0.44
     adsorption
    0.44
    strom
    0.44
    Activations Density 0.000%

    No Known Activations