© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 32166
    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
    イド
    0.23
     दीर्घ
    0.22
    깎
    0.22
     ग्राह
    0.22
    емости
    0.22
    frast
    0.22
     If
    0.22
     пол
    0.22
     عنها
    0.22
     ಗೋ
    0.22
    POSITIVE LOGITS
    ृह
    0.21
    吨
    0.20
     homosexuality
    0.19
    essages
    0.19
     humbly
    0.19
    DIVISION
    0.19
     Van
    0.19
     امور
    0.18
     suggestive
    0.18
    countery
    0.18
    Activations Density 0.000%

    No Known Activations