© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 44208
    Prev
    Next
    INDEX
    Explanations

    se trata

    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_13_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
    etr
    0.59
    ;">
    0.57
    st
    0.55
    elas
    0.55
    elos
    0.55
    els
    0.54
     complying
    0.51
        
    0.50
     formulating
    0.50
    ový
    0.49
    POSITIVE LOGITS
    ı
    0.57
     Nationalist
    0.56
    ان
    0.55
     reserva
    0.55
     deseja
    0.53
     partenza
    0.52
    ınız
    0.52
    İR
    0.52
     infest
    0.51
     प्यार
    0.51
    Activations Density 0.009%

    No Known Activations