© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 12-GEMMASCOPE-2-TRANSCODER-262K
    7. 201284
    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_12_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
    μός
    0.62
    
    0.57
    ме
    0.52
    வதற்காக
    0.52
    ид
    0.51
    ваи
    0.51
    istos
    0.50
     сфор
    0.50
     СА
    0.49
    obal
    0.49
    POSITIVE LOGITS
     '
    0.57
    ère
    0.56
    Ter
    0.56
     pouvait
    0.55
     mortgage
    0.55
    curvature
    0.54
     Président
    0.52
    ूर
    0.51
    AUTH
    0.51
    ocalypse
    0.51
    Activations Density 0.000%

    No Known Activations