© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28259
    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_10_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
    ocarcinoma
    0.52
    0
    0.51
    스러
    0.50
    uretics
    0.49
    ту
    0.49
    tutorial
    0.48
    articolo
    0.47
    ﻖ
    0.47
    Contacts
    0.46
    ﻘ
    0.46
    POSITIVE LOGITS
    ir
    0.49
    ↵
    0.42
     riche
    0.42
                         
    0.42
     elkaar
    0.42
    格
    0.41
    也将
    0.41
    శ్వ
    0.40
     greens
    0.40
     alman
    0.40
    Activations Density 0.000%

    No Known Activations