© 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. 58323
    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
    μοί
    0.57
     Antrag
    0.55
     moisturizing
    0.54
    SubSystem
    0.54
    션
    0.54
    arag
    0.53
     arousal
    0.52
     morphogenesis
    0.51
    temperatur
    0.51
     It
    0.50
    POSITIVE LOGITS
    }'
    0.58
     игровой
    0.56
    ную
    0.53
    ch
    0.50
    ötz
    0.50
    éreo
    0.49
    り
    0.49
    ri
    0.47
    use
    0.47
     resc
    0.47
    Activations Density 0.000%

    No Known Activations