© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173672
    Prev
    Next
    INDEX
    Explanations

    directions assignment

    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
     gains
    0.22
     Phase
    0.21
    ют
    0.21
     lighter
    0.21
     can
    0.21
     Host
    0.21
    zyn
    0.21
    l
    0.20
    Database
    0.20
     supports
    0.19
    POSITIVE LOGITS
    ៥
    0.23
     conteúdos
    0.23
     sculpting
    0.22
     ácidos
    0.21
    строва
    0.21
    marshaller
    0.21
     menurun
    0.21
    
    0.21
    ოლი
    0.21
     depresión
    0.21
    Activations Density 0.002%

    No Known Activations