© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91037
    Prev
    Next
    INDEX
    Explanations

    Livingstone

    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_11_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
     quienes
    0.62
     crecer
    0.62
    ת
    0.61
     producir
    0.61
     autént
    0.60
     realista
    0.58
     aprender
    0.57
     crear
    0.56
     Seguridad
    0.56
    釷
    0.56
    POSITIVE LOGITS
     tijekom
    0.48
    周
    0.48
     Banerjee
    0.46
    Lake
    0.45
    Interruptions
    0.45
    Dong
    0.45
    Banana
    0.45
    一级
    0.45
    0.45
    Bened
    0.44
    Activations Density 0.019%

    No Known Activations