© 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. 27854
    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
     Flows
    0.59
     Tools
    0.52
    d
    0.52
     Happy
    0.51
    Tools
    0.50
    Happy
    0.48
     Audio
    0.48
     Increases
    0.48
    Flow
    0.46
     Creates
    0.46
    POSITIVE LOGITS
     ደረጃ
    0.64
     isomerization
    0.58
     کشت
    0.57
     grasslands
    0.54
     ਡ
    0.53
     vineyards
    0.52
     پکڑ
    0.50
     ಜ
    0.50
     роках
    0.50
     حکومت
    0.50
    Activations Density 0.000%

    No Known Activations