© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 16895
    Prev
    Next
    INDEX
    Explanations

    magazine name

    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_15_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
     apuestas
    0.23
     grayscale
    0.22
    umbling
    0.22
     شرطونه
    0.22
    indungan
    0.21
    咵
    0.21
    涉及
    0.20
     wearables
    0.20
    orbidity
    0.20
     ټینس
    0.20
    POSITIVE LOGITS
                     
    0.24
    нер
    0.24
    AS
    0.22
     Gemeinde
    0.22
     considere
    0.21
                    
    0.21
                        
    0.21
    뚝
    0.21
             
    0.21
    AL
    0.21
    Activations Density 0.002%

    No Known Activations