© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 205583
    Prev
    Next
    INDEX
    Explanations

    processes, methods, strategies, techniques

    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
    Negative Logits
    setTextColor
    0.24
     peptid
    0.23
     atuais
    0.23
    ेशंस
    0.22
    S
    0.22
     handmade
    0.22
    TISE
    0.22
    MS
    0.21
    FAM
    0.21
     allies
    0.21
    POSITIVE LOGITS
    edLeft
    0.24
    
    0.23
     Oeste
    0.22
     Kola
    0.22
    icherweise
    0.22
     dobro
    0.22
    istered
    0.22
     misma
    0.22
    elijkheid
    0.21
    峩
    0.21
    Activations Density 0.010%

    No Known Activations