© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 172384
    Prev
    Next
    INDEX
    Explanations

    analyzing problematic questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    st
    0.51
     Per
    0.43
     Dutchman
    0.42
     Daily
    0.42
    j
    0.42
    Z
    0.41
     Car
    0.41
    ystem
    0.41
     do
    0.40
    aciones
    0.40
    POSITIVE LOGITS
    
    0.46
    
    0.46
     thirteen
    0.43
     ໜອງ
    0.43
     múltiplos
    0.43
    咅
    0.43
    ングル
    0.42
    áját
    0.42
     corresponds
    0.42
     innumerable
    0.42
    Activations Density 0.011%

    No Known Activations