© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 194160
    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
     ¼
    0.51
    뺨
    0.48
    论文
    0.47
     heiß
    0.47
     حياة
    0.47
    comfortable
    0.46
     Hälfte
    0.46
     நடி
    0.46
     Massage
    0.45
     তু
    0.45
    POSITIVE LOGITS
    c
    0.65
    t
    0.63
     ancients
    0.51
    𝐂
    0.50
     precipitate
    0.50
     and
    0.49
    ዃ
    0.49
     ибо
    0.49
     quale
    0.48
     curtailed
    0.48
    Activations Density 0.000%

    No Known Activations