© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 151071
    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_18_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
     Hood
    0.46
    eder
    0.44
    DataContext
    0.43
     Ə
    0.42
     gently
    0.42
     ә
    0.42
    toBeTruthy
    0.42
     quietly
    0.41
     hồn
    0.41
     laughed
    0.41
    POSITIVE LOGITS
    壤
    0.57
    و
    0.54
     gesam
    0.53
    యో
    0.53
    체의
    0.52
    𝐰
    0.51
    समाज
    0.48
     gesamte
    0.48
     betas
    0.47
    구
    0.47
    Activations Density 0.000%

    No Known Activations