© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 58882
    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_11_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
    麹
    0.51
     महाग
    0.50
    饥
    0.50
    美食
    0.50
    会場
    0.50
    FRONT
    0.50
     numai
    0.50
    楼
    0.49
     cinema
    0.48
    峰
    0.48
    POSITIVE LOGITS
    an
    0.58
    un
    0.55
    anik
    0.53
    uk
    0.50
    in
    0.49
    im
    0.48
     by
    0.47
    uck
    0.47
    sons
    0.47
    failed
    0.47
    Activations Density 0.000%

    No Known Activations