© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80092
    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
    Insurance
    0.17
     сча
    0.17
    តិ
    0.16
    헙
    0.16
    鐒
    0.16
    ति
    0.15
    Fb
    0.15
    IP
    0.15
     Campaigns
    0.15
    Supp
    0.15
    POSITIVE LOGITS
     McCain
    0.18
     Birken
    0.17
     MSM
    0.17
     coca
    0.15
     ermög
    0.15
    מצע
    0.15
     прямо
    0.14
     Pflicht
    0.14
     přímo
    0.14
     Glendale
    0.14
    Activations Density 0.000%

    No Known Activations